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

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

Neuron 4709 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: 1.2382. Min Range: -1.2382

Max Act: 1.2382. Min Act: -0.0000

Data Index: 881815 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.1626. Min Act: -0.0000

Data Index: 361203 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1304992 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0297. Min Act: 0.0000

Data Index: 408230 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0191. Min Act: -0.0000

Data Index: 266101 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1350635 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0014. Min Act: -0.0000

Data Index: 892229 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9862. Min Act: -0.0000

Data Index: 268373 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9561. Min Act: -0.0000

Data Index: 777357 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9518. Min Act: -0.0000

Data Index: 608979 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8685. Min Act: 0.0000

Data Index: 721341 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1032778 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8607. Min Act: -0.0000

Data Index: 134218 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8743. Min Act: -0.0000

Data Index: 941415 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8506. Min Act: -0.0000

Data Index: 387867 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1251020 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1220014 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8605. Min Act: -0.0000

Data Index: 261212 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8877. Min Act: -0.0000

Data Index: 548138 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.8061. Min Act: -0.0000

Data Index: 98363 (C4 (Web Text))

Max Activating Token Index: 609