Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2096 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1359094 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1135702 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4610. Min Act: -0.0000

Data Index: 99416 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4696. Min Act: -0.0000

Data Index: 2839 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4830. Min Act: -0.0001

Data Index: 1099041 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1306811 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4196. Min Act: -0.0001

Data Index: 98641 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4618. Min Act: -0.0000

Data Index: 442377 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4451. Min Act: -0.0000

Data Index: 393913 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4321. Min Act: -0.0000

Data Index: 535356 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1013604 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4182. Min Act: -0.0000

Data Index: 940091 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1035612 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4264. Min Act: 0.0001

Data Index: 466449 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1199584 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4123. Min Act: -0.0000

Data Index: 372788 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1186326 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1178581 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4224. Min Act: -0.0000

Data Index: 385990 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4029. Min Act: -0.0000

Data Index: 17337 (C4 (Web Text))

Max Activating Token Index: 862