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

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

Neuron 642 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: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0005

Data Index: 1307142 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0179. Min Act: -0.0005

Data Index: 727278 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1159351 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0166. Min Act: -0.0006

Data Index: 4230 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0163. Min Act: -0.0006

Data Index: 656790 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0158. Min Act: -0.0006

Data Index: 421426 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0164. Min Act: -0.0006

Data Index: 367318 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0160. Min Act: -0.0005

Data Index: 1108025 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0151. Min Act: -0.0006

Data Index: 485833 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0145. Min Act: -0.0006

Data Index: 783537 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0153. Min Act: -0.0006

Data Index: 82804 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0148. Min Act: -0.0005

Data Index: 1128779 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0148. Min Act: -0.0006

Data Index: 170505 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0148. Min Act: -0.0006

Data Index: 274149 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0147. Min Act: -0.0006

Data Index: 978032 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0140. Min Act: -0.0006

Data Index: 447177 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0145. Min Act: -0.0006

Data Index: 896015 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1104035 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1164185 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0151. Min Act: -0.0006

Data Index: 63377 (C4 (Web Text))

Max Activating Token Index: 926