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

Dataset: Open Web Text

Neuron 1196 in Layer 3

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: 3.8164. Min Range: -3.8164

Max Act: 3.8164. Min Act: -0.1700

Data Index: 6656251 (Open Web Text)

Max Activating Token Index: 69

Text #1

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.8055. Min Act: -0.1700

Data Index: 7069536 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7804. Min Act: -0.1700

Data Index: 654856 (Open Web Text)

Max Activating Token Index: 152

Text #3

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7743. Min Act: -0.1700

Data Index: 6752281 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7601. Min Act: -0.1700

Data Index: 1921795 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7514. Min Act: -0.1700

Data Index: 7469755 (Open Web Text)

Max Activating Token Index: 196

Text #6

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.8059. Min Act: -0.1700

Data Index: 654557 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7332. Min Act: -0.1700

Data Index: 7884520 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7674. Min Act: -0.1700

Data Index: 977826 (Open Web Text)

Max Activating Token Index: 390

Text #9

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7296. Min Act: -0.1700

Data Index: 3353223 (Open Web Text)

Max Activating Token Index: 449

Text #10

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7383. Min Act: -0.1700

Data Index: 3712151 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7344. Min Act: -0.1700

Data Index: 2187041 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7347. Min Act: -0.1700

Data Index: 6123831 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7429. Min Act: -0.1700

Data Index: 998511 (Open Web Text)

Max Activating Token Index: 702

Text #14

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7096. Min Act: -0.1700

Data Index: 8345319 (Open Web Text)

Max Activating Token Index: 569

Text #15

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6958. Min Act: -0.1700

Data Index: 5171734 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.7184. Min Act: -0.1700

Data Index: 414584 (Open Web Text)

Max Activating Token Index: 349

Text #17

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6903. Min Act: -0.1700

Data Index: 621530 (Open Web Text)

Max Activating Token Index: 265

Text #18

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6432. Min Act: -0.1700

Data Index: 3653935 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.8164. Min Range: -3.8164

Max Act: 3.6481. Min Act: -0.1700

Data Index: 6703207 (Open Web Text)

Max Activating Token Index: 74