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

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

Neuron 1034 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2686. Min Range: -1.2686

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1353919 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.2686. Min Range: -1.2686

Max Act: 1.1366. Min Act: -0.0000

Data Index: 410599 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.2686. Min Range: -1.2686

Max Act: 1.0481. Min Act: -0.0000

Data Index: 428133 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.9730. Min Act: -0.0000

Data Index: 943997 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.8771. Min Act: -0.0000

Data Index: 995039 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1108104 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1004537 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7970. Min Act: -0.0000

Data Index: 963034 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1198547 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1007541 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7625. Min Act: -0.0000

Data Index: 575694 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.8369. Min Act: -0.0000

Data Index: 43516 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7824. Min Act: -0.0000

Data Index: 43092 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7986. Min Act: -0.0000

Data Index: 361737 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7701. Min Act: -0.0000

Data Index: 955936 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7596. Min Act: 0.0000

Data Index: 241080 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1138396 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7433. Min Act: -0.0000

Data Index: 632902 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7393. Min Act: -0.0000

Data Index: 356348 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.2686. Min Range: -1.2686

Max Act: 0.7351. Min Act: -0.0000

Data Index: 276600 (C4 (Web Text))

Max Activating Token Index: 176