Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0001

Data Index: 15742 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0316. Min Act: -0.0001

Data Index: 69800 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0276. Min Act: -0.0001

Data Index: 879415 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1365759 (Python Code)

Max Activating Token Index: 807

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1505038 (Python Code)

Max Activating Token Index: 99

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0270. Min Act: -0.0001

Data Index: 245203 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0270. Min Act: -0.0001

Data Index: 899650 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1257523 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0265. Min Act: -0.0001

Data Index: 987967 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0248. Min Act: -0.0001

Data Index: 947158 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0237. Min Act: -0.0001

Data Index: 487078 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1275743 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1264614 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0242. Min Act: -0.0001

Data Index: 136914 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0243. Min Act: -0.0001

Data Index: 244538 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0257. Min Act: -0.0001

Data Index: 257619 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0223. Min Act: -0.0001

Data Index: 123991 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0256. Min Act: -0.0001

Data Index: 924447 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1412033 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0242. Min Act: -0.0001

Data Index: 254227 (C4 (Web Text))

Max Activating Token Index: 436