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

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

Neuron 4349 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: 1.5630. Min Range: -1.5630

Max Act: 1.4213. Min Act: -0.0002

Data Index: 1097963 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.5630. Min Act: -0.0002

Data Index: 758495 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2999. Min Act: -0.0002

Data Index: 174887 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.4268. Min Act: -0.0002

Data Index: 1233822 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.4089. Min Act: -0.0002

Data Index: 1150589 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3498. Min Act: -0.0002

Data Index: 838959 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.4145. Min Act: -0.0002

Data Index: 1053132 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3101. Min Act: -0.0002

Data Index: 982787 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3546. Min Act: -0.0002

Data Index: 1236268 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2123. Min Act: -0.0002

Data Index: 130125 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3024. Min Act: -0.0002

Data Index: 639326 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3592. Min Act: -0.0002

Data Index: 147007 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.3203. Min Act: -0.0002

Data Index: 1004955 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2490. Min Act: -0.0002

Data Index: 364477 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2373. Min Act: -0.0002

Data Index: 13641 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.0970. Min Act: -0.0002

Data Index: 75705 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.2176. Min Act: -0.0002

Data Index: 1097647 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.1337. Min Act: -0.0002

Data Index: 1250158 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.1371. Min Act: -0.0002

Data Index: 1318706 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.5630. Min Range: -1.5630

Max Act: 1.1162. Min Act: -0.0002

Data Index: 845453 (C4 (Web Text))

Max Activating Token Index: 242