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

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

Neuron 1982 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0003

Data Index: 431361 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1203864 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0340. Min Act: -0.0003

Data Index: 769619 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0330. Min Act: -0.0003

Data Index: 318335 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0317. Min Act: -0.0003

Data Index: 396713 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0318. Min Act: -0.0002

Data Index: 940548 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0313. Min Act: -0.0003

Data Index: 340745 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0312. Min Act: -0.0002

Data Index: 770534 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1143901 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0297. Min Act: -0.0003

Data Index: 411558 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0302. Min Act: -0.0003

Data Index: 355097 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1141128 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0300. Min Act: -0.0003

Data Index: 922268 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0299. Min Act: -0.0002

Data Index: 81083 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0297. Min Act: -0.0003

Data Index: 440282 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0301. Min Act: -0.0003

Data Index: 110354 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0293. Min Act: -0.0002

Data Index: 856838 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0293. Min Act: -0.0003

Data Index: 137330 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0290. Min Act: -0.0003

Data Index: 631136 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0290. Min Act: -0.0003

Data Index: 965255 (C4 (Web Text))

Max Activating Token Index: 188