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

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

Neuron 678 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: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0006

Data Index: 406302 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1199734 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0174. Min Act: -0.0006

Data Index: 93052 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0165. Min Act: -0.0006

Data Index: 642353 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0158. Min Act: -0.0006

Data Index: 302403 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0165. Min Act: -0.0006

Data Index: 198237 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0163. Min Act: -0.0006

Data Index: 762204 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0167. Min Act: -0.0006

Data Index: 154869 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1509506 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1217347 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0163. Min Act: -0.0006

Data Index: 909866 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0163. Min Act: -0.0006

Data Index: 264318 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1373935 (Python Code)

Max Activating Token Index: 880

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1054427 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0149. Min Act: -0.0006

Data Index: 902370 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0155. Min Act: -0.0006

Data Index: 495059 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1328871 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1081204 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0006

Data Index: 503705 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0150. Min Act: -0.0006

Data Index: 773916 (C4 (Web Text))

Max Activating Token Index: 456