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

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

Neuron 2023 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: 0.0397. Min Range: -0.0397

Max Act: 0.0367. Min Act: -0.0003

Data Index: 293876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0003

Data Index: 698813 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1037883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0320. Min Act: -0.0003

Data Index: 960563 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1361030 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0299. Min Act: -0.0003

Data Index: 563467 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1078006 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0299. Min Act: -0.0003

Data Index: 555091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0258. Min Act: -0.0003

Data Index: 395795 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0359. Min Act: -0.0003

Data Index: 884136 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0211. Min Act: -0.0003

Data Index: 556305 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0323. Min Act: -0.0003

Data Index: 736318 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0265. Min Act: -0.0003

Data Index: 745358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0278. Min Act: -0.0003

Data Index: 565357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0334. Min Act: -0.0004

Data Index: 818981 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1070359 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1234476 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0275. Min Act: -0.0003

Data Index: 735963 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0266. Min Act: -0.0003

Data Index: 66268 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0261. Min Act: -0.0003

Data Index: 702415 (C4 (Web Text))

Max Activating Token Index: 1023