Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1619 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0221. Min Act: -0.0006

Data Index: 235254 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0205. Min Act: -0.0006

Data Index: 936446 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0006

Data Index: 590540 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0215. Min Act: -0.0006

Data Index: 338912 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0215. Min Act: -0.0006

Data Index: 27756 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0201. Min Act: -0.0006

Data Index: 474435 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0191. Min Act: -0.0006

Data Index: 561766 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0199. Min Act: -0.0006

Data Index: 33513 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0184. Min Act: -0.0006

Data Index: 305996 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0176. Min Act: -0.0006

Data Index: 327211 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0187. Min Act: -0.0006

Data Index: 583767 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0174. Min Act: -0.0006

Data Index: 319163 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0163. Min Act: -0.0006

Data Index: 394264 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0156. Min Act: -0.0006

Data Index: 144766 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0173. Min Act: -0.0006

Data Index: 943370 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0154. Min Act: -0.0006

Data Index: 802266 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0168. Min Act: -0.0006

Data Index: 722008 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1262711 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1190209 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1237785 (C4 (Web Text))

Max Activating Token Index: 583