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

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

Neuron 5039 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: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0002

Data Index: 121736 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0296. Min Act: -0.0002

Data Index: 151653 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1343583 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0290. Min Act: -0.0002

Data Index: 440207 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0289. Min Act: -0.0002

Data Index: 136377 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0283. Min Act: -0.0002

Data Index: 137885 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0283. Min Act: -0.0002

Data Index: 777228 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0289. Min Act: -0.0002

Data Index: 561342 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0289. Min Act: -0.0002

Data Index: 656798 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0289. Min Act: -0.0002

Data Index: 335506 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0288. Min Act: -0.0002

Data Index: 519795 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0282. Min Act: -0.0002

Data Index: 523936 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0288. Min Act: -0.0002

Data Index: 131656 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0287. Min Act: -0.0002

Data Index: 720371 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0287. Min Act: -0.0002

Data Index: 635027 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0287. Min Act: -0.0002

Data Index: 580990 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1201070 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0286. Min Act: -0.0002

Data Index: 262101 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1027484 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0286. Min Act: -0.0002

Data Index: 488135 (C4 (Web Text))

Max Activating Token Index: 259