Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4990 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.6577. Min Act: -0.0000

Data Index: 1308316 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.5629. Min Act: -0.0000

Data Index: 1140449 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.4371. Min Act: -0.0000

Data Index: 71424 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.5682. Min Act: -0.0000

Data Index: 754456 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.3988. Min Act: -0.0000

Data Index: 146676 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.3418. Min Act: -0.0000

Data Index: 119761 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.4692. Min Act: -0.0000

Data Index: 122188 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.1185. Min Act: -0.0000

Data Index: 746775 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1318493 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.4120. Min Act: -0.0000

Data Index: 989848 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.1372. Min Act: -0.0000

Data Index: 548779 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.3808. Min Act: -0.0000

Data Index: 1237665 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.2452. Min Act: -0.0000

Data Index: 928093 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.3356. Min Act: -0.0000

Data Index: 1235454 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.0869. Min Act: -0.0000

Data Index: 547187 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.0631. Min Act: -0.0000

Data Index: 413510 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.0167. Min Act: -0.0000

Data Index: 692389 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 2.6577. Min Range: -2.6577

Max Act: 2.0339. Min Act: -0.0000

Data Index: 690432 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 2.6577. Min Range: -2.6577

Max Act: 1.7823. Min Act: -0.0000

Data Index: 970834 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 2.6577. Min Range: -2.6577

Max Act: 1.6944. Min Act: -0.0000

Data Index: 88615 (C4 (Web Text))

Max Activating Token Index: 851