Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4523 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1019980 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1012932 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0306. Min Act: -0.0001

Data Index: 243494 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0312. Min Act: -0.0001

Data Index: 571292 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1305926 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0255. Min Act: -0.0001

Data Index: 576943 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0261. Min Act: -0.0001

Data Index: 930138 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0244. Min Act: -0.0001

Data Index: 827566 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0245. Min Act: -0.0001

Data Index: 678442 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0237. Min Act: -0.0001

Data Index: 726954 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0216. Min Act: -0.0001

Data Index: 600171 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1088222 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0215. Min Act: -0.0001

Data Index: 428083 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0205. Min Act: -0.0001

Data Index: 43366 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0227. Min Act: -0.0001

Data Index: 528210 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1063254 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0214. Min Act: -0.0001

Data Index: 834111 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0222. Min Act: -0.0001

Data Index: 205526 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0211. Min Act: -0.0001

Data Index: 470165 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0199. Min Act: -0.0001

Data Index: 158116 (C4 (Web Text))

Max Activating Token Index: 231