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

Dataset: Open Web Text

Neuron 1967 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: 3.5098. Min Range: -3.5098

Max Act: 3.5098. Min Act: -0.1700

Data Index: 4452096 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3640. Min Act: -0.1700

Data Index: 8089113 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3560. Min Act: -0.1700

Data Index: 7390538 (Open Web Text)

Max Activating Token Index: 659

Text #3

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3216. Min Act: -0.1700

Data Index: 7475623 (Open Web Text)

Max Activating Token Index: 329

Text #4

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3261. Min Act: -0.1700

Data Index: 2908192 (Open Web Text)

Max Activating Token Index: 298

Text #5

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1316557 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.3202. Min Act: -0.1700

Data Index: 3326193 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2815. Min Act: -0.1700

Data Index: 3481081 (Open Web Text)

Max Activating Token Index: 348

Text #8

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2989. Min Act: -0.1700

Data Index: 8800767 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2775. Min Act: -0.1700

Data Index: 8800763 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2574. Min Act: -0.1700

Data Index: 4804552 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2485. Min Act: -0.1700

Data Index: 5761921 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2181. Min Act: -0.1700

Data Index: 5273230 (Open Web Text)

Max Activating Token Index: 573

Text #13

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2261. Min Act: -0.1700

Data Index: 1068246 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2271. Min Act: -0.1700

Data Index: 4815572 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2257. Min Act: -0.1700

Data Index: 7151761 (Open Web Text)

Max Activating Token Index: 45

Text #16

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2295. Min Act: -0.1700

Data Index: 5408391 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1958. Min Act: -0.1700

Data Index: 5907830 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.1862. Min Act: -0.1700

Data Index: 4161824 (Open Web Text)

Max Activating Token Index: 113

Text #19

Max Range: 3.5098. Min Range: -3.5098

Max Act: 3.2207. Min Act: -0.1700

Data Index: 7424261 (Open Web Text)

Max Activating Token Index: 550