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

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

Neuron 5100 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0499. Min Act: -0.0002

Data Index: 747877 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1542283 (Python Code)

Max Activating Token Index: 563

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0533. Min Act: -0.0002

Data Index: 107004 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0528. Min Act: -0.0002

Data Index: 469617 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0535. Min Act: -0.0002

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0541. Min Act: -0.0002

Data Index: 853940 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0507. Min Act: -0.0002

Data Index: 378267 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0465. Min Act: -0.0002

Data Index: 712745 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0471. Min Act: -0.0002

Data Index: 739885 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0486. Min Act: -0.0002

Data Index: 226080 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0459. Min Act: -0.0002

Data Index: 340214 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1054961 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0481. Min Act: -0.0002

Data Index: 372222 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0466. Min Act: -0.0002

Data Index: 361254 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1344296 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0461. Min Act: -0.0002

Data Index: 676966 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0475. Min Act: -0.0002

Data Index: 70586 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1206866 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0441. Min Act: -0.0002

Data Index: 74759 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0434. Min Act: -0.0002

Data Index: 38286 (C4 (Web Text))

Max Activating Token Index: 182