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

Dataset: Open Web Text

Neuron 2222 in Layer 0

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: 5.2258. Min Range: -5.2258

Max Act: 5.2258. Min Act: -0.1700

Data Index: 8059469 (Open Web Text)

Max Activating Token Index: 88

Text #1

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.1145. Min Act: -0.1700

Data Index: 5424496 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.1164. Min Act: -0.1700

Data Index: 3962921 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.1457. Min Act: -0.1700

Data Index: 2915817 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.0966. Min Act: -0.1700

Data Index: 1873422 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.0345. Min Act: -0.1700

Data Index: 8204634 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.0280. Min Act: -0.1700

Data Index: 6879503 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.0391. Min Act: -0.1700

Data Index: 7577896 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.0415. Min Act: -0.1700

Data Index: 4304144 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.0069. Min Act: -0.1700

Data Index: 146508 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9765. Min Act: -0.1700

Data Index: 1365160 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9639. Min Act: -0.1700

Data Index: 371938 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9791. Min Act: -0.1700

Data Index: 3141537 (Open Web Text)

Max Activating Token Index: 809

Text #13

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9856. Min Act: -0.1700

Data Index: 4481382 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9622. Min Act: -0.1700

Data Index: 4468272 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9629. Min Act: -0.1700

Data Index: 960394 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9746. Min Act: -0.1700

Data Index: 7528413 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9793. Min Act: -0.1700

Data Index: 7054801 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9565. Min Act: -0.1700

Data Index: 6753032 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.9595. Min Act: -0.1700

Data Index: 4554711 (Open Web Text)

Max Activating Token Index: 6