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

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

Neuron 2801 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.7872. Min Act: -0.0001

Data Index: 1308600 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.5355. Min Act: -0.0001

Data Index: 851689 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.4047. Min Act: -0.0001

Data Index: 1275561 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.7084. Min Act: -0.0001

Data Index: 1257617 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.5882. Min Act: -0.0001

Data Index: 1351326 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.6203. Min Act: -0.0001

Data Index: 677591 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.4268. Min Act: -0.0001

Data Index: 958403 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.3500. Min Act: -0.0001

Data Index: 142173 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.3657. Min Act: -0.0001

Data Index: 61220 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.5151. Min Act: -0.0001

Data Index: 706871 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.3956. Min Act: -0.0001

Data Index: 80534 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.3424. Min Act: -0.0001

Data Index: 873104 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.4190. Min Act: -0.0001

Data Index: 104582 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.4490. Min Act: -0.0001

Data Index: 384891 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1350165 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.3634. Min Act: -0.0001

Data Index: 559974 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.2336. Min Act: -0.0001

Data Index: 1253231 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.2223. Min Act: -0.0001

Data Index: 126477 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.3154. Min Act: -0.0001

Data Index: 748083 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 1.7872. Min Range: -1.7872

Max Act: 1.2802. Min Act: -0.0001

Data Index: 455024 (C4 (Web Text))

Max Activating Token Index: 635