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

Dataset: Open Web Text

Neuron 2306 in Layer 5

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: 5.4545. Min Range: -5.4545

Max Act: 5.4545. Min Act: -0.1700

Data Index: 3132615 (Open Web Text)

Max Activating Token Index: 275

Text #1

Max Range: 5.4545. Min Range: -5.4545

Max Act: 5.0481. Min Act: -0.1700

Data Index: 36000 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.9468. Min Act: -0.1700

Data Index: 3882653 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.9253. Min Act: -0.1700

Data Index: 7375410 (Open Web Text)

Max Activating Token Index: 117

Text #4

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8729. Min Act: -0.1700

Data Index: 6540343 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8817. Min Act: -0.1700

Data Index: 2813406 (Open Web Text)

Max Activating Token Index: 844

Text #6

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8131. Min Act: -0.1700

Data Index: 7768557 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8460. Min Act: -0.1700

Data Index: 7359650 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8549. Min Act: -0.1700

Data Index: 2742711 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8199. Min Act: -0.1700

Data Index: 5924046 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8281. Min Act: -0.1700

Data Index: 2552090 (Open Web Text)

Max Activating Token Index: 855

Text #11

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8297. Min Act: -0.1700

Data Index: 5474890 (Open Web Text)

Max Activating Token Index: 716

Text #12

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8103. Min Act: -0.1700

Data Index: 8139333 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.8075. Min Act: -0.1700

Data Index: 6734929 (Open Web Text)

Max Activating Token Index: 948

Text #14

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.7633. Min Act: -0.1700

Data Index: 1205681 (Open Web Text)

Max Activating Token Index: 278

Text #15

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.7638. Min Act: -0.1700

Data Index: 683747 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.7548. Min Act: -0.1700

Data Index: 4263757 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.7613. Min Act: -0.1700

Data Index: 2104015 (Open Web Text)

Max Activating Token Index: 572

Text #18

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.7568. Min Act: -0.1700

Data Index: 2001607 (Open Web Text)

Max Activating Token Index: 180

Text #19

Max Range: 5.4545. Min Range: -5.4545

Max Act: 4.7537. Min Act: -0.1700

Data Index: 7325791 (Open Web Text)

Max Activating Token Index: 673