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

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

Neuron 2410 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6693. Min Act: -0.0000

Data Index: 112863 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6479. Min Act: 0.0000

Data Index: 1607784 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6251. Min Act: -0.0000

Data Index: 323433 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6897. Min Act: -0.0000

Data Index: 669901 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5769. Min Act: -0.0000

Data Index: 661290 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5126. Min Act: -0.0000

Data Index: 400094 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1231570 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1209458 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6019. Min Act: -0.0000

Data Index: 231870 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1326195 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5571. Min Act: -0.0000

Data Index: 577515 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5232. Min Act: -0.0000

Data Index: 488591 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1280137 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5373. Min Act: 0.0000

Data Index: 1052968 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5793. Min Act: -0.0000

Data Index: 34248 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5264. Min Act: -0.0000

Data Index: 726364 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6024. Min Act: -0.0000

Data Index: 382170 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5207. Min Act: 0.0000

Data Index: 1194798 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5327. Min Act: -0.0000

Data Index: 196394 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5436. Min Act: -0.0000

Data Index: 563237 (C4 (Web Text))

Max Activating Token Index: 555