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

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

Neuron 4084 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: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1407155 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1412642 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0439. Min Act: -0.0003

Data Index: 904038 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1574242 (Python Code)

Max Activating Token Index: 668

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1501358 (Python Code)

Max Activating Token Index: 327

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0386. Min Act: -0.0003

Data Index: 608835 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0378. Min Act: -0.0003

Data Index: 832743 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1546447 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1293223 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0321. Min Act: -0.0003

Data Index: 130892 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1654012 (Python Code)

Max Activating Token Index: 190

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0302. Min Act: -0.0003

Data Index: 307490 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1539116 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0305. Min Act: -0.0003

Data Index: 12191 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0313. Min Act: -0.0003

Data Index: 693488 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0310. Min Act: -0.0003

Data Index: 314188 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0304. Min Act: -0.0003

Data Index: 523132 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0301. Min Act: -0.0003

Data Index: 105827 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1421171 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1598511 (Python Code)

Max Activating Token Index: 1000