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

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

Neuron 2706 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0003

Data Index: 40181 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1424952 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1518735 (Python Code)

Max Activating Token Index: 560

Text #3

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0192. Min Act: -0.0003

Data Index: 734810 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1636929 (Python Code)

Max Activating Token Index: 568

Text #5

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1558662 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1424144 (Python Code)

Max Activating Token Index: 684

Text #7

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1609651 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0186. Min Act: -0.0003

Data Index: 325853 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0191. Min Act: -0.0003

Data Index: 925470 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1531466 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1397863 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0174. Min Act: -0.0003

Data Index: 47922 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1587516 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0174. Min Act: -0.0003

Data Index: 238437 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1423856 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0186. Min Act: -0.0003

Data Index: 412040 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0185. Min Act: -0.0003

Data Index: 259098 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1566272 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1484195 (Python Code)

Max Activating Token Index: 570