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

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

Neuron 983 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: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0006

Data Index: 102340 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0196. Min Act: -0.0006

Data Index: 888333 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1179301 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0192. Min Act: -0.0006

Data Index: 558245 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0187. Min Act: -0.0006

Data Index: 43670 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1240061 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0172. Min Act: -0.0006

Data Index: 249024 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0171. Min Act: -0.0006

Data Index: 762511 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0164. Min Act: -0.0006

Data Index: 806636 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0168. Min Act: -0.0006

Data Index: 40367 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0170. Min Act: -0.0006

Data Index: 715569 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0165. Min Act: -0.0006

Data Index: 713441 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1104738 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0168. Min Act: -0.0006

Data Index: 365558 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0160. Min Act: -0.0006

Data Index: 424019 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1005683 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0154. Min Act: -0.0006

Data Index: 335853 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1366644 (Python Code)

Max Activating Token Index: 219

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0156. Min Act: -0.0006

Data Index: 56079 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0156. Min Act: -0.0006

Data Index: 824791 (C4 (Web Text))

Max Activating Token Index: 1007