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

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

Neuron 633 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: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0006

Data Index: 535529 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1346792 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1353009 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0205. Min Act: -0.0006

Data Index: 252636 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0204. Min Act: -0.0006

Data Index: 488304 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1154667 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0192. Min Act: -0.0006

Data Index: 736996 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0196. Min Act: -0.0006

Data Index: 851195 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1317214 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1130567 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0184. Min Act: -0.0006

Data Index: 931295 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0192. Min Act: -0.0006

Data Index: 107924 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0187. Min Act: -0.0006

Data Index: 502748 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1257241 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1243141 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0187. Min Act: -0.0006

Data Index: 65074 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0190. Min Act: -0.0006

Data Index: 956244 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0181. Min Act: -0.0006

Data Index: 576310 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0176. Min Act: -0.0006

Data Index: 613617 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1145604 (C4 (Web Text))

Max Activating Token Index: 44