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

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

Neuron 3397 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1199433 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1239465 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3317. Min Act: -0.0000

Data Index: 516879 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3242. Min Act: -0.0000

Data Index: 438013 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.3158. Min Act: -0.0000

Data Index: 336282 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.2019. Min Act: -0.0000

Data Index: 993905 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.2821. Min Act: -0.0000

Data Index: 206957 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.2250. Min Act: -0.0000

Data Index: 612343 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1297535 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.2520. Min Act: -0.0000

Data Index: 641834 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.1279. Min Act: -0.0000

Data Index: 694809 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.1273. Min Act: -0.0000

Data Index: 218317 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1195469 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.0865. Min Act: -0.0000

Data Index: 513963 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1178053 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.1356. Min Act: -0.0000

Data Index: 193655 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.0665. Min Act: -0.0000

Data Index: 732699 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.0545. Min Act: -0.0000

Data Index: 327618 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1153278 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.6978. Min Range: -1.6978

Max Act: 1.0100. Min Act: -0.0000

Data Index: 968038 (C4 (Web Text))

Max Activating Token Index: 367