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

Dataset: Open Web Text

Neuron 94 in Layer 4

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: 4.1922. Min Range: -4.1922

Max Act: 4.1922. Min Act: -0.1700

Data Index: 5651608 (Open Web Text)

Max Activating Token Index: 959

Text #1

Max Range: 4.1922. Min Range: -4.1922

Max Act: 4.1530. Min Act: -0.1700

Data Index: 8097549 (Open Web Text)

Max Activating Token Index: 881

Text #2

Max Range: 4.1922. Min Range: -4.1922

Max Act: 4.1434. Min Act: -0.1700

Data Index: 3561925 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 4.1922. Min Range: -4.1922

Max Act: 4.0163. Min Act: -0.1700

Data Index: 5512574 (Open Web Text)

Max Activating Token Index: 504

Text #4

Max Range: 4.1922. Min Range: -4.1922

Max Act: 4.0298. Min Act: -0.1700

Data Index: 8652957 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 4.1922. Min Range: -4.1922

Max Act: 4.0442. Min Act: -0.1700

Data Index: 5003889 (Open Web Text)

Max Activating Token Index: 1011

Text #6

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9866. Min Act: -0.1700

Data Index: 620334 (Open Web Text)

Max Activating Token Index: 133

Text #7

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9777. Min Act: -0.1700

Data Index: 5367050 (Open Web Text)

Max Activating Token Index: 412

Text #8

Max Range: 4.1922. Min Range: -4.1922

Max Act: 4.0101. Min Act: -0.1700

Data Index: 6804359 (Open Web Text)

Max Activating Token Index: 292

Text #9

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9954. Min Act: -0.1700

Data Index: 6384533 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9628. Min Act: -0.1700

Data Index: 8683154 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9199. Min Act: -0.1700

Data Index: 3675717 (Open Web Text)

Max Activating Token Index: 307

Text #12

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9357. Min Act: -0.1700

Data Index: 7142223 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9171. Min Act: -0.1700

Data Index: 7524653 (Open Web Text)

Max Activating Token Index: 300

Text #14

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9439. Min Act: -0.1700

Data Index: 4324979 (Open Web Text)

Max Activating Token Index: 177

Text #15

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9273. Min Act: -0.1700

Data Index: 7947180 (Open Web Text)

Max Activating Token Index: 941

Text #16

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9363. Min Act: -0.1700

Data Index: 8223373 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9481. Min Act: -0.1700

Data Index: 1232222 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9409. Min Act: -0.1700

Data Index: 1686523 (Open Web Text)

Max Activating Token Index: 65

Text #19

Max Range: 4.1922. Min Range: -4.1922

Max Act: 3.9220. Min Act: -0.1700

Data Index: 1733322 (Open Web Text)

Max Activating Token Index: 160