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

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

Neuron 3333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1281464 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.4388. Min Act: -0.0000

Data Index: 405937 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3841. Min Act: -0.0000

Data Index: 148694 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3581. Min Act: -0.0000

Data Index: 601273 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3019. Min Act: -0.0000

Data Index: 449603 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2952. Min Act: -0.0000

Data Index: 296502 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2300. Min Act: -0.0000

Data Index: 106339 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2008. Min Act: -0.0000

Data Index: 425924 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1033539 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.0659. Min Act: -0.0000

Data Index: 143463 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.0907. Min Act: -0.0000

Data Index: 904883 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.0872. Min Act: -0.0000

Data Index: 806292 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.0554. Min Act: -0.0000

Data Index: 930356 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.0280. Min Act: -0.0000

Data Index: 71477 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.9998. Min Act: -0.0000

Data Index: 198233 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.9501. Min Act: -0.0000

Data Index: 447390 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.9570. Min Act: -0.0000

Data Index: 765234 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.9242. Min Act: -0.0000

Data Index: 214797 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.0117. Min Act: -0.0000

Data Index: 727249 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.9679. Min Act: -0.0000

Data Index: 931235 (C4 (Web Text))

Max Activating Token Index: 490