Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5552 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.6940. Min Act: -0.0000

Data Index: 743935 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.4286. Min Act: -0.0000

Data Index: 687782 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.3897. Min Act: -0.0000

Data Index: 379641 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.1461. Min Act: -0.0000

Data Index: 715399 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.2661. Min Act: -0.0000

Data Index: 32685 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.1189. Min Act: -0.0000

Data Index: 1222430 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.3138. Min Act: -0.0000

Data Index: 991573 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.1598. Min Act: -0.0000

Data Index: 22551 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.1099. Min Act: -0.0000

Data Index: 713 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.0092. Min Act: -0.0000

Data Index: 538895 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 2.6940. Min Range: -2.6940

Max Act: 1.9614. Min Act: -0.0000

Data Index: 1160578 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.1845. Min Act: -0.0000

Data Index: 804393 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.0327. Min Act: -0.0000

Data Index: 421432 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.0306. Min Act: -0.0000

Data Index: 19956 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.0110. Min Act: -0.0000

Data Index: 146026 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 2.6940. Min Range: -2.6940

Max Act: 2.0723. Min Act: -0.0000

Data Index: 553879 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 2.6940. Min Range: -2.6940

Max Act: 1.8871. Min Act: -0.0000

Data Index: 802267 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 2.6940. Min Range: -2.6940

Max Act: 1.6843. Min Act: -0.0000

Data Index: 160146 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 2.6940. Min Range: -2.6940

Max Act: 1.8795. Min Act: -0.0000

Data Index: 671912 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 2.6940. Min Range: -2.6940

Max Act: 1.7497. Min Act: -0.0000

Data Index: 109065 (C4 (Web Text))

Max Activating Token Index: 141