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

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

Neuron 1270 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0003

Data Index: 841423 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0201. Min Act: -0.0004

Data Index: 989913 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0193. Min Act: -0.0003

Data Index: 866885 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0186. Min Act: -0.0004

Data Index: 550756 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0192. Min Act: -0.0003

Data Index: 20836 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0183. Min Act: -0.0002

Data Index: 547377 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0176. Min Act: -0.0002

Data Index: 631757 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0177. Min Act: -0.0003

Data Index: 652185 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0172. Min Act: -0.0003

Data Index: 36583 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0176. Min Act: -0.0003

Data Index: 983964 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0178. Min Act: -0.0002

Data Index: 392711 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0175. Min Act: -0.0003

Data Index: 213792 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0174. Min Act: -0.0004

Data Index: 193033 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0181. Min Act: -0.0002

Data Index: 785735 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0172. Min Act: -0.0003

Data Index: 162272 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0172. Min Act: -0.0003

Data Index: 903631 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0168. Min Act: -0.0003

Data Index: 260572 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0171. Min Act: -0.0003

Data Index: 714889 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1299443 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1271382 (C4 (Web Text))

Max Activating Token Index: 132