Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2957 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1855. Min Range: -4.1855

Max Act: 4.1855. Min Act: -0.0000

Data Index: 916866 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 4.1855. Min Range: -4.1855

Max Act: 3.3211. Min Act: -0.0000

Data Index: 1242957 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 4.1855. Min Range: -4.1855

Max Act: 3.0536. Min Act: -0.0000

Data Index: 752493 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 4.1855. Min Range: -4.1855

Max Act: 3.1316. Min Act: -0.0000

Data Index: 646386 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 4.1855. Min Range: -4.1855

Max Act: 3.1508. Min Act: -0.0000

Data Index: 54729 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 4.1855. Min Range: -4.1855

Max Act: 3.0040. Min Act: -0.0000

Data Index: 158832 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.5290. Min Act: -0.0000

Data Index: 884282 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.6264. Min Act: -0.0000

Data Index: 91491 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.7527. Min Act: -0.0000

Data Index: 1107223 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.6973. Min Act: -0.0000

Data Index: 1056873 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.5518. Min Act: -0.0000

Data Index: 512081 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.6545. Min Act: -0.0000

Data Index: 1132986 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.6063. Min Act: -0.0000

Data Index: 521285 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.4136. Min Act: -0.0000

Data Index: 687630 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.3897. Min Act: -0.0000

Data Index: 106573 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.5137. Min Act: -0.0000

Data Index: 851547 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.3773. Min Act: -0.0000

Data Index: 1205744 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.3849. Min Act: -0.0000

Data Index: 197190 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.4972. Min Act: -0.0000

Data Index: 523038 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 4.1855. Min Range: -4.1855

Max Act: 2.7464. Min Act: -0.0000

Data Index: 659662 (C4 (Web Text))

Max Activating Token Index: 603