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

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

Neuron 14 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: 0.0181. Min Range: -0.0181

Max Act: 0.0181. Min Act: -0.0006

Data Index: 7340 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0161. Min Act: -0.0006

Data Index: 991988 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0159. Min Act: -0.0006

Data Index: 816676 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0160. Min Act: -0.0006

Data Index: 630799 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0163. Min Act: -0.0006

Data Index: 90623 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0168. Min Act: -0.0006

Data Index: 985007 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1188934 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0164. Min Act: -0.0006

Data Index: 79553 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1604685 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0152. Min Act: -0.0006

Data Index: 647503 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0159. Min Act: -0.0006

Data Index: 500643 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0151. Min Act: -0.0006

Data Index: 281111 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0154. Min Act: -0.0006

Data Index: 121853 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1229306 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0156. Min Act: -0.0006

Data Index: 199548 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0152. Min Act: -0.0006

Data Index: 356308 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1182415 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0152. Min Act: -0.0006

Data Index: 39712 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0148. Min Act: -0.0006

Data Index: 428088 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0147. Min Act: -0.0006

Data Index: 312023 (C4 (Web Text))

Max Activating Token Index: 612