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

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

Neuron 1549 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: 0.4318. Min Range: -0.4318

Max Act: 0.4070. Min Act: -0.0002

Data Index: 596344 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.4150. Min Act: -0.0002

Data Index: 125559 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3867. Min Act: -0.0002

Data Index: 832277 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.4318. Min Act: -0.0002

Data Index: 939930 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3759. Min Act: -0.0002

Data Index: 618024 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.4044. Min Act: -0.0002

Data Index: 319459 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3511. Min Act: -0.0002

Data Index: 556349 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3289. Min Act: -0.0002

Data Index: 351633 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3145. Min Act: -0.0002

Data Index: 540680 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3347. Min Act: -0.0002

Data Index: 1144423 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3553. Min Act: -0.0002

Data Index: 471304 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3683. Min Act: -0.0002

Data Index: 877688 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3660. Min Act: -0.0002

Data Index: 522635 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3733. Min Act: -0.0002

Data Index: 732496 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3460. Min Act: -0.0002

Data Index: 249725 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3738. Min Act: -0.0002

Data Index: 848419 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3199. Min Act: -0.0002

Data Index: 1310406 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3517. Min Act: -0.0002

Data Index: 347560 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3184. Min Act: -0.0002

Data Index: 674863 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3504. Min Act: -0.0002

Data Index: 208584 (C4 (Web Text))

Max Activating Token Index: 624