Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 302 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1050416 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0163. Min Act: -0.0003

Data Index: 501672 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0156. Min Act: -0.0004

Data Index: 856493 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0160. Min Act: -0.0003

Data Index: 479961 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0157. Min Act: -0.0004

Data Index: 497605 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1179160 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1068071 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0153. Min Act: -0.0004

Data Index: 82979 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0152. Min Act: -0.0004

Data Index: 483991 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0003

Data Index: 425857 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0155. Min Act: -0.0004

Data Index: 529230 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0148. Min Act: -0.0003

Data Index: 909174 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0155. Min Act: -0.0003

Data Index: 121702 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0003

Data Index: 512483 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1315198 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0004

Data Index: 157010 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1099218 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0003

Data Index: 542087 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0151. Min Act: -0.0003

Data Index: 246134 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1146304 (C4 (Web Text))

Max Activating Token Index: 873