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

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

Neuron 2316 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0002

Data Index: 788888 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0314. Min Act: -0.0002

Data Index: 730462 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0300. Min Act: -0.0002

Data Index: 887063 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0276. Min Act: -0.0002

Data Index: 279289 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1462821 (Python Code)

Max Activating Token Index: 229

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0288. Min Act: -0.0002

Data Index: 169840 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1069122 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0279. Min Act: -0.0002

Data Index: 169593 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1177862 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0251. Min Act: -0.0002

Data Index: 432849 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0270. Min Act: -0.0002

Data Index: 132469 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0263. Min Act: -0.0002

Data Index: 498013 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0266. Min Act: -0.0002

Data Index: 630136 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1338547 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1566620 (Python Code)

Max Activating Token Index: 462

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0251. Min Act: -0.0002

Data Index: 329191 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1240681 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0250. Min Act: -0.0002

Data Index: 527818 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1032649 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0241. Min Act: -0.0002

Data Index: 780236 (C4 (Web Text))

Max Activating Token Index: 148