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

Dataset: Open Web Text

Neuron 1878 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: 4.8938. Min Range: -4.8938

Max Act: 4.8938. Min Act: -0.1700

Data Index: 377552 (Open Web Text)

Max Activating Token Index: 956

Text #1

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.8589. Min Act: -0.1700

Data Index: 4011233 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.8246. Min Act: -0.1700

Data Index: 7488867 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.8085. Min Act: -0.1700

Data Index: 313324 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.8028. Min Act: -0.1700

Data Index: 1760877 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7910. Min Act: -0.1700

Data Index: 684651 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7797. Min Act: -0.1700

Data Index: 1282376 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7787. Min Act: -0.1700

Data Index: 3760188 (Open Web Text)

Max Activating Token Index: 842

Text #8

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7433. Min Act: -0.1700

Data Index: 7542274 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7374. Min Act: -0.1700

Data Index: 7945386 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7142. Min Act: -0.1700

Data Index: 1778042 (Open Web Text)

Max Activating Token Index: 109

Text #11

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7202. Min Act: -0.1700

Data Index: 443103 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7063. Min Act: -0.1700

Data Index: 5765367 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7171. Min Act: -0.1700

Data Index: 8086912 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.7030. Min Act: -0.1700

Data Index: 447874 (Open Web Text)

Max Activating Token Index: 168

Text #15

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.6490. Min Act: -0.1700

Data Index: 82805 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.6756. Min Act: -0.1700

Data Index: 6876040 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.6789. Min Act: -0.1700

Data Index: 6336353 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.6346. Min Act: -0.1700

Data Index: 1857861 (Open Web Text)

Max Activating Token Index: 714

Text #19

Max Range: 4.8938. Min Range: -4.8938

Max Act: 4.6566. Min Act: -0.1700

Data Index: 3474229 (Open Web Text)

Max Activating Token Index: 353