< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0907. Min Act: -0.1700

Data Index: 8318959 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0673. Min Act: -0.1700

Data Index: 3384755 (Open Web Text)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0532. Min Act: -0.1700

Data Index: 6645313 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0567. Min Act: -0.1700

Data Index: 3064693 (Open Web Text)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0177. Min Act: -0.1700

Data Index: 1798967 (Open Web Text)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0077. Min Act: -0.1700

Data Index: 8440140 (Open Web Text)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0083. Min Act: -0.1700

Data Index: 2696112 (Open Web Text)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9920. Min Act: -0.1700

Data Index: 3676832 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0907. Min Range: -2.0907

Max Act: 2.0014. Min Act: -0.1700

Data Index: 6323911 (Open Web Text)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9979. Min Act: -0.1700

Data Index: 5886420 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9819. Min Act: -0.1700

Data Index: 2171429 (Open Web Text)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9837. Min Act: -0.1700

Data Index: 1714973 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9746. Min Act: -0.1700

Data Index: 5202747 (Open Web Text)

Max Activating Token Index: 252

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9683. Min Act: -0.1700

Data Index: 3659217 (Open Web Text)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9746. Min Act: -0.1700

Data Index: 6306721 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9854. Min Act: -0.1700

Data Index: 4158153 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9703. Min Act: -0.1700

Data Index: 2419566 (Open Web Text)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9577. Min Act: -0.1700

Data Index: 6255063 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9483. Min Act: -0.1700

Data Index: 2171428 (Open Web Text)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0907. Min Range: -2.0907

Max Act: 1.9613. Min Act: -0.1700

Data Index: 6951853 (Open Web Text)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #19