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

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

Neuron 2987 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0003

Data Index: 273313 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0382. Min Act: -0.0003

Data Index: 672353 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0368. Min Act: -0.0004

Data Index: 302413 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1343568 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0358. Min Act: -0.0003

Data Index: 663059 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0350. Min Act: -0.0003

Data Index: 388905 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0339. Min Act: -0.0003

Data Index: 458683 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0315. Min Act: -0.0003

Data Index: 263032 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1067743 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1117006 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0333. Min Act: -0.0003

Data Index: 441647 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0334. Min Act: -0.0003

Data Index: 972907 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1215984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0308. Min Act: -0.0003

Data Index: 845923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1227114 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1120985 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0309. Min Act: -0.0003

Data Index: 538449 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1123415 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0330. Min Act: -0.0003

Data Index: 83842 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1290502 (C4 (Web Text))

Max Activating Token Index: 207