Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3264 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0003

Data Index: 34925 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1187787 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1166201 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0198. Min Act: -0.0003

Data Index: 663388 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1051344 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1181542 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0184. Min Act: -0.0002

Data Index: 965831 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0183. Min Act: -0.0003

Data Index: 746342 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0178. Min Act: -0.0002

Data Index: 57383 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1061665 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0174. Min Act: -0.0003

Data Index: 410742 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1119256 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0180. Min Act: -0.0003

Data Index: 99425 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1114143 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0175. Min Act: -0.0003

Data Index: 474079 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1323921 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0167. Min Act: -0.0002

Data Index: 427623 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0167. Min Act: -0.0003

Data Index: 447354 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1201957 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0166. Min Act: -0.0003

Data Index: 992800 (C4 (Web Text))

Max Activating Token Index: 940