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

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

Neuron 4200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.8411. Min Act: -0.0000

Data Index: 266287 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.4846. Min Act: -0.0001

Data Index: 1198424 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.3743. Min Act: -0.0000

Data Index: 1056370 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.4819. Min Act: -0.0001

Data Index: 551494 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2480. Min Act: -0.0000

Data Index: 262598 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.1519. Min Act: -0.0001

Data Index: 508197 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2668. Min Act: -0.0000

Data Index: 1266847 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.3655. Min Act: -0.0000

Data Index: 766044 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2310. Min Act: -0.0000

Data Index: 221366 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.1809. Min Act: -0.0001

Data Index: 802387 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.0474. Min Act: -0.0001

Data Index: 536068 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2528. Min Act: -0.0001

Data Index: 1084459 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.1328. Min Act: -0.0000

Data Index: 814677 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.1427. Min Act: -0.0000

Data Index: 1320577 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2368. Min Act: -0.0000

Data Index: 485576 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2384. Min Act: -0.0001

Data Index: 459787 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.1800. Min Act: -0.0000

Data Index: 302162 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.1965. Min Act: -0.0000

Data Index: 629322 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2045. Min Act: -0.0000

Data Index: 244519 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 2.8411. Min Range: -2.8411

Max Act: 2.2577. Min Act: -0.0001

Data Index: 680992 (C4 (Web Text))

Max Activating Token Index: 545