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

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

Neuron 2011 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: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0006

Data Index: 831654 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1297034 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0208. Min Act: -0.0006

Data Index: 943569 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0211. Min Act: -0.0006

Data Index: 18723 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0183. Min Act: -0.0006

Data Index: 293581 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1033947 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1251374 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1268324 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0204. Min Act: -0.0006

Data Index: 139717 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0190. Min Act: -0.0006

Data Index: 506030 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0202. Min Act: -0.0006

Data Index: 746518 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1037910 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1040383 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1177123 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0157. Min Act: -0.0006

Data Index: 275413 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1171386 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0187. Min Act: -0.0006

Data Index: 119110 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0159. Min Act: -0.0006

Data Index: 860251 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1109260 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0199. Min Act: -0.0006

Data Index: 922003 (C4 (Web Text))

Max Activating Token Index: 816