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

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

Neuron 1032 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1617640 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0158. Min Act: -0.0006

Data Index: 776198 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1061353 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0157. Min Act: -0.0007

Data Index: 1098741 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1314689 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0152. Min Act: -0.0006

Data Index: 177701 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0154. Min Act: -0.0006

Data Index: 369891 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0151. Min Act: -0.0006

Data Index: 701092 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0151. Min Act: -0.0006

Data Index: 614630 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1416137 (Python Code)

Max Activating Token Index: 214

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0140. Min Act: -0.0006

Data Index: 466235 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0150. Min Act: -0.0006

Data Index: 981415 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0152. Min Act: -0.0006

Data Index: 993552 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1597004 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0006

Data Index: 53045 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0006

Data Index: 203776 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0006

Data Index: 126071 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0006

Data Index: 214073 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1133773 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1523998 (Python Code)

Max Activating Token Index: 354