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

Dataset: Open Web Text

Neuron 1468 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: 4.7104. Min Range: -4.7104

Max Act: 4.7104. Min Act: -0.1700

Data Index: 1700564 (Open Web Text)

Max Activating Token Index: 165

Text #1

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.6210. Min Act: -0.1700

Data Index: 7238239 (Open Web Text)

Max Activating Token Index: 72

Text #2

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.5366. Min Act: -0.1700

Data Index: 3648444 (Open Web Text)

Max Activating Token Index: 327

Text #3

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.5159. Min Act: -0.1700

Data Index: 5789451 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.4891. Min Act: -0.1700

Data Index: 2432891 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.5318. Min Act: -0.1700

Data Index: 4481464 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.4660. Min Act: -0.1700

Data Index: 7128419 (Open Web Text)

Max Activating Token Index: 319

Text #7

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.4464. Min Act: -0.1700

Data Index: 6799659 (Open Web Text)

Max Activating Token Index: 918

Text #8

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.4109. Min Act: -0.1700

Data Index: 1644441 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3945. Min Act: -0.1700

Data Index: 7020279 (Open Web Text)

Max Activating Token Index: 926

Text #10

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.4145. Min Act: -0.1700

Data Index: 8598371 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3602. Min Act: -0.1700

Data Index: 4251325 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3589. Min Act: -0.1700

Data Index: 6682939 (Open Web Text)

Max Activating Token Index: 832

Text #13

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3454. Min Act: -0.1700

Data Index: 137916 (Open Web Text)

Max Activating Token Index: 699

Text #14

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3598. Min Act: -0.1700

Data Index: 6208311 (Open Web Text)

Max Activating Token Index: 422

Text #15

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3505. Min Act: -0.1700

Data Index: 5647461 (Open Web Text)

Max Activating Token Index: 390

Text #16

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3255. Min Act: -0.1700

Data Index: 4649471 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3379. Min Act: -0.1700

Data Index: 5351732 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3269. Min Act: -0.1700

Data Index: 4861598 (Open Web Text)

Max Activating Token Index: 526

Text #19

Max Range: 4.7104. Min Range: -4.7104

Max Act: 4.3403. Min Act: -0.1700

Data Index: 4983049 (Open Web Text)

Max Activating Token Index: 986