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

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

Neuron 2745 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.6901. Min Act: -0.0000

Data Index: 997888 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.6236. Min Act: -0.0000

Data Index: 630151 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.6318. Min Act: -0.0000

Data Index: 238841 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.6219. Min Act: -0.0000

Data Index: 685832 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5908. Min Act: -0.0000

Data Index: 268567 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1155177 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5340. Min Act: -0.0000

Data Index: 848487 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5444. Min Act: 0.0000

Data Index: 1236993 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1300382 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5485. Min Act: -0.0000

Data Index: 952590 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5368. Min Act: -0.0000

Data Index: 212652 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.4920. Min Act: -0.0000

Data Index: 762851 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5404. Min Act: 0.0000

Data Index: 149149 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5343. Min Act: -0.0000

Data Index: 333780 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5465. Min Act: -0.0000

Data Index: 423815 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5162. Min Act: -0.0000

Data Index: 858471 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1005636 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5384. Min Act: -0.0000

Data Index: 485481 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.5055. Min Act: -0.0000

Data Index: 291410 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.6901. Min Range: -0.6901

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1261823 (C4 (Web Text))

Max Activating Token Index: 369