Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 675 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0006

Data Index: 943192 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0203. Min Act: -0.0006

Data Index: 904609 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0006

Data Index: 917009 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1089850 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0192. Min Act: -0.0006

Data Index: 705749 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1088776 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0006

Data Index: 568435 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0189. Min Act: -0.0006

Data Index: 458160 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1326660 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0188. Min Act: -0.0006

Data Index: 593518 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0174. Min Act: -0.0006

Data Index: 524859 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0189. Min Act: -0.0006

Data Index: 983350 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0190. Min Act: -0.0006

Data Index: 564597 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0176. Min Act: -0.0006

Data Index: 435940 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1285382 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0184. Min Act: -0.0006

Data Index: 121398 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1017292 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0187. Min Act: -0.0006

Data Index: 995942 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0175. Min Act: -0.0006

Data Index: 833400 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1097399 (C4 (Web Text))

Max Activating Token Index: 208