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

Dataset: Open Web Text

Neuron 1387 in Layer 1

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: 1.8169. Min Range: -1.8169

Max Act: 1.8169. Min Act: -0.1698

Data Index: 6806539 (Open Web Text)

Max Activating Token Index: 151

Text #1

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7824. Min Act: -0.1700

Data Index: 3772130 (Open Web Text)

Max Activating Token Index: 240

Text #2

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7684. Min Act: -0.1700

Data Index: 4063438 (Open Web Text)

Max Activating Token Index: 851

Text #3

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7603. Min Act: -0.1698

Data Index: 4873086 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7580. Min Act: -0.1693

Data Index: 2271978 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7360. Min Act: -0.1700

Data Index: 7030035 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7247. Min Act: -0.1700

Data Index: 6882083 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7182. Min Act: -0.1700

Data Index: 3738832 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7108. Min Act: -0.1700

Data Index: 7611337 (Open Web Text)

Max Activating Token Index: 1011

Text #9

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7108. Min Act: -0.1699

Data Index: 5152348 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7154. Min Act: -0.1700

Data Index: 7670575 (Open Web Text)

Max Activating Token Index: 459

Text #11

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7200. Min Act: -0.1700

Data Index: 7883494 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7086. Min Act: -0.1699

Data Index: 6270725 (Open Web Text)

Max Activating Token Index: 206

Text #13

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7005. Min Act: -0.1700

Data Index: 489635 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7015. Min Act: -0.1700

Data Index: 5223187 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.6992. Min Act: -0.1700

Data Index: 6527161 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.6880. Min Act: -0.1700

Data Index: 4868325 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.6824. Min Act: -0.1700

Data Index: 6788607 (Open Web Text)

Max Activating Token Index: 298

Text #18

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.6936. Min Act: -0.1693

Data Index: 349735 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.6894. Min Act: -0.1698

Data Index: 2256417 (Open Web Text)

Max Activating Token Index: 40