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

Dataset: Open Web Text

Neuron 296 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: 3.6886. Min Range: -3.6886

Max Act: 3.6505. Min Act: -0.1700

Data Index: 2281244 (Open Web Text)

Max Activating Token Index: 830

Text #1

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6886. Min Act: -0.1700

Data Index: 1366062 (Open Web Text)

Max Activating Token Index: 612

Text #2

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6370. Min Act: -0.1700

Data Index: 6105365 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6632. Min Act: -0.1700

Data Index: 440397 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6483. Min Act: -0.1700

Data Index: 6805456 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6405. Min Act: -0.1700

Data Index: 6999053 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6493. Min Act: -0.1700

Data Index: 7029695 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6275. Min Act: -0.1700

Data Index: 5076193 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6191. Min Act: -0.1700

Data Index: 4992240 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5993. Min Act: -0.1700

Data Index: 8683672 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6045. Min Act: -0.1700

Data Index: 7110027 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6157. Min Act: -0.1700

Data Index: 2531902 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5986. Min Act: -0.1700

Data Index: 2495697 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6345. Min Act: -0.1700

Data Index: 1250204 (Open Web Text)

Max Activating Token Index: 789

Text #14

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6184. Min Act: -0.1700

Data Index: 8208 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6339. Min Act: -0.1700

Data Index: 6783143 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.6060. Min Act: -0.1700

Data Index: 3112692 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1882104 (Open Web Text)

Max Activating Token Index: 720

Text #18

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5705. Min Act: -0.1700

Data Index: 4705376 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 3.6886. Min Range: -3.6886

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1463409 (Open Web Text)

Max Activating Token Index: 339