Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 342 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.3165. Min Act: -0.0001

Data Index: 979782 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2663. Min Act: -0.0001

Data Index: 780980 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2746. Min Act: -0.0001

Data Index: 878318 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2562. Min Act: -0.0002

Data Index: 1092787 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2614. Min Act: -0.0001

Data Index: 830394 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2539. Min Act: -0.0001

Data Index: 775761 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2554. Min Act: -0.0001

Data Index: 902809 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2510. Min Act: -0.0002

Data Index: 386120 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2491. Min Act: -0.0002

Data Index: 620863 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2457. Min Act: -0.0001

Data Index: 1191319 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1154594 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2425. Min Act: -0.0001

Data Index: 727315 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2512. Min Act: -0.0001

Data Index: 658422 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2388. Min Act: -0.0001

Data Index: 842092 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2384. Min Act: -0.0001

Data Index: 401939 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2451. Min Act: -0.0001

Data Index: 694749 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2442. Min Act: -0.0001

Data Index: 791675 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2379. Min Act: -0.0001

Data Index: 313691 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2455. Min Act: -0.0002

Data Index: 1287458 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2594. Min Act: -0.0001

Data Index: 684938 (C4 (Web Text))

Max Activating Token Index: 89