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

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

Neuron 3885 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.4907. Min Act: -0.0000

Data Index: 533218 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.4351. Min Act: -0.0000

Data Index: 437860 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.4252. Min Act: -0.0000

Data Index: 568423 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.4245. Min Act: -0.0000

Data Index: 742615 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.4160. Min Act: 0.0002

Data Index: 632260 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.4236. Min Act: -0.0000

Data Index: 167252 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3906. Min Act: -0.0000

Data Index: 261895 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3785. Min Act: -0.0000

Data Index: 891155 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1430783 (Python Code)

Max Activating Token Index: 663

Text #9

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1005065 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1481086 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1446994 (Python Code)

Max Activating Token Index: 753

Text #12

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3468. Min Act: -0.0000

Data Index: 464568 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3671. Min Act: -0.0000

Data Index: 519307 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3530. Min Act: -0.0000

Data Index: 689351 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3640. Min Act: -0.0000

Data Index: 572718 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1648019 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1468229 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3444. Min Act: -0.0000

Data Index: 604525 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.4907. Min Range: -0.4907

Max Act: 0.3361. Min Act: -0.0000

Data Index: 822027 (C4 (Web Text))

Max Activating Token Index: 585