Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1131 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0002

Data Index: 599192 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0554. Min Act: -0.0002

Data Index: 386584 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0566. Min Act: -0.0002

Data Index: 887580 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0502. Min Act: -0.0002

Data Index: 979163 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1077923 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0533. Min Act: -0.0002

Data Index: 772242 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0519. Min Act: -0.0002

Data Index: 977381 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0519. Min Act: -0.0002

Data Index: 907623 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0496. Min Act: -0.0002

Data Index: 974377 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0492. Min Act: -0.0002

Data Index: 102843 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0494. Min Act: -0.0002

Data Index: 421339 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0497. Min Act: -0.0002

Data Index: 379994 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0475. Min Act: -0.0002

Data Index: 396779 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1346671 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0485. Min Act: -0.0002

Data Index: 40311 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1345013 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1328260 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1174912 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0466. Min Act: -0.0002

Data Index: 299943 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0485. Min Act: -0.0002

Data Index: 390596 (C4 (Web Text))

Max Activating Token Index: 924