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

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

Neuron 3747 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0002

Data Index: 51222 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1062012 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0471. Min Act: -0.0002

Data Index: 664926 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0457. Min Act: -0.0002

Data Index: 431111 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0442. Min Act: -0.0002

Data Index: 319113 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1038260 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0448. Min Act: -0.0002

Data Index: 907037 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0447. Min Act: -0.0002

Data Index: 922501 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0447. Min Act: -0.0002

Data Index: 267099 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1094513 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0446. Min Act: -0.0002

Data Index: 527676 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1138267 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0445. Min Act: -0.0002

Data Index: 561831 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0443. Min Act: -0.0002

Data Index: 808416 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0434. Min Act: -0.0002

Data Index: 729765 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0434. Min Act: -0.0002

Data Index: 254873 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0440. Min Act: -0.0002

Data Index: 693656 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0442. Min Act: -0.0002

Data Index: 45211 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0441. Min Act: -0.0002

Data Index: 360740 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1024522 (C4 (Web Text))

Max Activating Token Index: 158