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

Dataset: Open Web Text

Neuron 804 in Layer 2

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: 1.3507. Min Range: -1.3507

Max Act: 1.3482. Min Act: -0.1700

Data Index: 7197949 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.3507. Min Act: -0.1700

Data Index: 2387573 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.3405. Min Act: -0.1700

Data Index: 7776529 (Open Web Text)

Max Activating Token Index: 736

Text #3

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.3117. Min Act: -0.1685

Data Index: 5988128 (Open Web Text)

Max Activating Token Index: 527

Text #4

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.3094. Min Act: -0.1700

Data Index: 3327777 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.3129. Min Act: -0.1700

Data Index: 2401583 (Open Web Text)

Max Activating Token Index: 784

Text #6

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.3096. Min Act: -0.1696

Data Index: 8046648 (Open Web Text)

Max Activating Token Index: 936

Text #7

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.3074. Min Act: -0.1697

Data Index: 769523 (Open Web Text)

Max Activating Token Index: 283

Text #8

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2936. Min Act: -0.1700

Data Index: 2401584 (Open Web Text)

Max Activating Token Index: 162

Text #9

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2741. Min Act: -0.1700

Data Index: 824232 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2765. Min Act: -0.1700

Data Index: 7797036 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2676. Min Act: -0.1700

Data Index: 8744987 (Open Web Text)

Max Activating Token Index: 826

Text #12

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2743. Min Act: -0.1700

Data Index: 8510374 (Open Web Text)

Max Activating Token Index: 715

Text #13

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2776. Min Act: -0.1699

Data Index: 3241598 (Open Web Text)

Max Activating Token Index: 318

Text #14

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2687. Min Act: -0.1700

Data Index: 3576905 (Open Web Text)

Max Activating Token Index: 588

Text #15

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2644. Min Act: -0.1700

Data Index: 3258290 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2584. Min Act: -0.1699

Data Index: 4333174 (Open Web Text)

Max Activating Token Index: 232

Text #17

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2587. Min Act: -0.1700

Data Index: 7846292 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2674. Min Act: -0.1700

Data Index: 4433751 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 1.3507. Min Range: -1.3507

Max Act: 1.2757. Min Act: -0.1700

Data Index: 3657154 (Open Web Text)

Max Activating Token Index: 561