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

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

Neuron 1520 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: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0003

Data Index: 688996 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0431. Min Act: -0.0003

Data Index: 596702 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1334704 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0378. Min Act: -0.0003

Data Index: 261646 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1138894 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1272168 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1119365 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1109262 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1117030 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1026167 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1171740 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0305. Min Act: -0.0003

Data Index: 356848 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0303. Min Act: -0.0003

Data Index: 692897 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1227635 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1251080 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0336. Min Act: -0.0003

Data Index: 261299 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1306089 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0281. Min Act: -0.0003

Data Index: 765902 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0297. Min Act: -0.0003

Data Index: 408536 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1233373 (C4 (Web Text))

Max Activating Token Index: 275