< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 258 in Layer 4

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: 2.3814. Min Range: -2.3814

Max Act: 2.3814. Min Act: -0.1700

Data Index: 6999605 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.3318. Min Act: -0.1700

Data Index: 7157791 (Open Web Text)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.3037. Min Act: -0.1700

Data Index: 4899656 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.3022. Min Act: -0.1700

Data Index: 2886637 (Open Web Text)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.2829. Min Act: -0.1700

Data Index: 3597232 (Open Web Text)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.2431. Min Act: -0.1700

Data Index: 337665 (Open Web Text)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.2338. Min Act: -0.1700

Data Index: 2455656 (Open Web Text)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.2335. Min Act: -0.1700

Data Index: 274954 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.2250. Min Act: -0.1700

Data Index: 3170978 (Open Web Text)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.2127. Min Act: -0.1700

Data Index: 1801295 (Open Web Text)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.2071. Min Act: -0.1700

Data Index: 1106054 (Open Web Text)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1981. Min Act: -0.1700

Data Index: 2951582 (Open Web Text)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1933. Min Act: -0.1700

Data Index: 4179925 (Open Web Text)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1783. Min Act: -0.1700

Data Index: 3976114 (Open Web Text)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1791. Min Act: -0.1700

Data Index: 4071234 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1639. Min Act: -0.1700

Data Index: 397799 (Open Web Text)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1796. Min Act: -0.1700

Data Index: 8659131 (Open Web Text)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1584. Min Act: -0.1700

Data Index: 6667671 (Open Web Text)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1710. Min Act: -0.1700

Data Index: 4929800 (Open Web Text)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3814. Min Range: -2.3814

Max Act: 2.1645. Min Act: -0.1700

Data Index: 6571117 (Open Web Text)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #19