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

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

Neuron 3743 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: 0.0340. Min Range: -0.0340

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1159572 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0003

Data Index: 10759 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0311. Min Act: -0.0003

Data Index: 194864 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0307. Min Act: -0.0003

Data Index: 445220 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0290. Min Act: -0.0003

Data Index: 384020 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0292. Min Act: -0.0003

Data Index: 740893 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0275. Min Act: -0.0003

Data Index: 716728 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1140302 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0284. Min Act: -0.0003

Data Index: 584196 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0277. Min Act: -0.0003

Data Index: 518003 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0266. Min Act: -0.0003

Data Index: 661952 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0256. Min Act: -0.0003

Data Index: 766761 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0260. Min Act: -0.0003

Data Index: 36709 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0278. Min Act: -0.0003

Data Index: 476327 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0282. Min Act: -0.0003

Data Index: 461515 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0275. Min Act: -0.0003

Data Index: 596040 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0280. Min Act: -0.0003

Data Index: 953986 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1200486 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0266. Min Act: -0.0003

Data Index: 325109 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1349764 (C4 (Web Text))

Max Activating Token Index: 609