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

Dataset: Open Web Text

Neuron 1543 in Layer 5

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: 3.3587. Min Range: -3.3587

Max Act: 3.3587. Min Act: -0.1700

Data Index: 5211027 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.3204. Min Act: -0.1700

Data Index: 7841936 (Open Web Text)

Max Activating Token Index: 335

Text #2

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.3039. Min Act: -0.1700

Data Index: 4538886 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.2790. Min Act: -0.1700

Data Index: 8682260 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.2591. Min Act: -0.1700

Data Index: 177295 (Open Web Text)

Max Activating Token Index: 199

Text #5

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.2604. Min Act: -0.1700

Data Index: 6201980 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.2048. Min Act: -0.1700

Data Index: 7792396 (Open Web Text)

Max Activating Token Index: 211

Text #7

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.2302. Min Act: -0.1700

Data Index: 6901262 (Open Web Text)

Max Activating Token Index: 525

Text #8

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.2056. Min Act: -0.1700

Data Index: 5652153 (Open Web Text)

Max Activating Token Index: 780

Text #9

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1862. Min Act: -0.1700

Data Index: 2579892 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1619. Min Act: -0.1700

Data Index: 4789992 (Open Web Text)

Max Activating Token Index: 618

Text #11

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1657. Min Act: -0.1700

Data Index: 3186927 (Open Web Text)

Max Activating Token Index: 733

Text #12

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1634. Min Act: -0.1700

Data Index: 2731089 (Open Web Text)

Max Activating Token Index: 238

Text #13

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1472. Min Act: -0.1700

Data Index: 8403929 (Open Web Text)

Max Activating Token Index: 827

Text #14

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1553. Min Act: -0.1700

Data Index: 7813238 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1844. Min Act: -0.1700

Data Index: 1548313 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1572. Min Act: -0.1700

Data Index: 5477091 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1420. Min Act: -0.1700

Data Index: 8509198 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1585. Min Act: -0.1700

Data Index: 6352313 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 3.3587. Min Range: -3.3587

Max Act: 3.1740. Min Act: -0.1700

Data Index: 8233683 (Open Web Text)

Max Activating Token Index: 921