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

Dataset: Open Web Text

Neuron 1949 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: 4.8494. Min Range: -4.8494

Max Act: 4.8494. Min Act: -0.1700

Data Index: 7172775 (Open Web Text)

Max Activating Token Index: 261

Text #1

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7973. Min Act: -0.1700

Data Index: 4825367 (Open Web Text)

Max Activating Token Index: 767

Text #2

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.8009. Min Act: -0.1700

Data Index: 4516456 (Open Web Text)

Max Activating Token Index: 122

Text #3

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7526. Min Act: -0.1700

Data Index: 2870479 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.8007. Min Act: -0.1700

Data Index: 3641096 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7551. Min Act: -0.1700

Data Index: 5828470 (Open Web Text)

Max Activating Token Index: 79

Text #6

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7291. Min Act: -0.1700

Data Index: 5736400 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7474. Min Act: -0.1700

Data Index: 8433023 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7244. Min Act: -0.1700

Data Index: 7748294 (Open Web Text)

Max Activating Token Index: 1016

Text #9

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7512. Min Act: -0.1700

Data Index: 6885792 (Open Web Text)

Max Activating Token Index: 649

Text #10

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7471. Min Act: -0.1700

Data Index: 7100661 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7197. Min Act: -0.1700

Data Index: 8777633 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7016. Min Act: -0.1700

Data Index: 1834630 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7211. Min Act: -0.1700

Data Index: 7624708 (Open Web Text)

Max Activating Token Index: 841

Text #14

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7089. Min Act: -0.1700

Data Index: 151816 (Open Web Text)

Max Activating Token Index: 674

Text #15

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7373. Min Act: -0.1700

Data Index: 7584974 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7286. Min Act: -0.1700

Data Index: 7252108 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.6918. Min Act: -0.1700

Data Index: 7194674 (Open Web Text)

Max Activating Token Index: 164

Text #18

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7371. Min Act: -0.1700

Data Index: 6157073 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 4.8494. Min Range: -4.8494

Max Act: 4.7051. Min Act: -0.1700

Data Index: 1941231 (Open Web Text)

Max Activating Token Index: 175