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

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

Neuron 877 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: 0.0188. Min Range: -0.0188

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1060002 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1134425 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0178. Min Act: -0.0006

Data Index: 626308 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0188. Min Act: -0.0006

Data Index: 340560 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0185. Min Act: -0.0006

Data Index: 362615 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0181. Min Act: -0.0006

Data Index: 885455 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1290578 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1191451 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0158. Min Act: -0.0006

Data Index: 81045 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0182. Min Act: -0.0006

Data Index: 603584 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0177. Min Act: -0.0006

Data Index: 297537 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0181. Min Act: -0.0006

Data Index: 741043 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0182. Min Act: -0.0006

Data Index: 897344 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1220727 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0170. Min Act: -0.0006

Data Index: 327103 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0172. Min Act: -0.0006

Data Index: 678248 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0167. Min Act: -0.0006

Data Index: 144671 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0156. Min Act: -0.0006

Data Index: 115847 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1150087 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0159. Min Act: -0.0006

Data Index: 624795 (C4 (Web Text))

Max Activating Token Index: 99