< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 25 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: 2.6076. Min Range: -2.6076

Max Act: 2.6076. Min Act: -0.1700

Data Index: 8112320 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.5569. Min Act: -0.1698

Data Index: 1317418 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.5219. Min Act: -0.1700

Data Index: 2627867 (Open Web Text)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.5296. Min Act: -0.1700

Data Index: 1317424 (Open Web Text)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.5366. Min Act: -0.1700

Data Index: 2575955 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.5021. Min Act: -0.1700

Data Index: 1317415 (Open Web Text)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4927. Min Act: -0.1700

Data Index: 7859546 (Open Web Text)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4717. Min Act: -0.1700

Data Index: 1219890 (Open Web Text)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4833. Min Act: -0.1700

Data Index: 2099709 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4823. Min Act: -0.1700

Data Index: 7743025 (Open Web Text)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4753. Min Act: -0.1700

Data Index: 8800166 (Open Web Text)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4836. Min Act: -0.1700

Data Index: 2007270 (Open Web Text)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4677. Min Act: -0.1700

Data Index: 7471482 (Open Web Text)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4480. Min Act: -0.1700

Data Index: 1317427 (Open Web Text)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4439. Min Act: -0.1700

Data Index: 6656699 (Open Web Text)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4412. Min Act: -0.1700

Data Index: 1068562 (Open Web Text)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4411. Min Act: -0.1700

Data Index: 3556292 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4483. Min Act: -0.1700

Data Index: 27154 (Open Web Text)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4430. Min Act: -0.1700

Data Index: 7246950 (Open Web Text)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6076. Min Range: -2.6076

Max Act: 2.4341. Min Act: -0.1700

Data Index: 1068563 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #19