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

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

Neuron 1422 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0210. Min Act: -0.0005

Data Index: 1159308 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0005

Data Index: 436556 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0211. Min Act: -0.0005

Data Index: 549171 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1307927 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0005

Data Index: 725678 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0194. Min Act: -0.0005

Data Index: 532016 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0005

Data Index: 105540 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0194. Min Act: -0.0005

Data Index: 333658 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0201. Min Act: -0.0005

Data Index: 566938 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0195. Min Act: -0.0005

Data Index: 193682 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0195. Min Act: -0.0005

Data Index: 46825 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0193. Min Act: -0.0005

Data Index: 796875 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1236633 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1440472 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0190. Min Act: -0.0005

Data Index: 1023001 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0177. Min Act: -0.0005

Data Index: 230030 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1042869 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0170. Min Act: -0.0005

Data Index: 218858 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0175. Min Act: -0.0005

Data Index: 988845 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0176. Min Act: -0.0005

Data Index: 901628 (C4 (Web Text))

Max Activating Token Index: 919