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

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

Neuron 1370 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: 0.0204. Min Range: -0.0204

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1301621 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0201. Min Act: -0.0006

Data Index: 886032 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0204. Min Act: -0.0006

Data Index: 366291 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0202. Min Act: -0.0006

Data Index: 879789 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0176. Min Act: -0.0006

Data Index: 883667 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0162. Min Act: -0.0006

Data Index: 812344 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1354548 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0170. Min Act: -0.0006

Data Index: 668710 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0163. Min Act: -0.0006

Data Index: 949053 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0168. Min Act: -0.0006

Data Index: 394074 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1255991 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0143. Min Act: -0.0006

Data Index: 376152 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0152. Min Act: -0.0006

Data Index: 861142 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1369989 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1234566 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0164. Min Act: -0.0006

Data Index: 334065 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1418331 (Python Code)

Max Activating Token Index: 433

Text #17

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0139. Min Act: -0.0006

Data Index: 83423 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0167. Min Act: -0.0006

Data Index: 900486 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0150. Min Act: -0.0006

Data Index: 910614 (C4 (Web Text))

Max Activating Token Index: 665