Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1079 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0005

Data Index: 1634529 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0331. Min Act: -0.0005

Data Index: 147739 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0342. Min Act: -0.0005

Data Index: 660916 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0323. Min Act: -0.0005

Data Index: 463884 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0328. Min Act: -0.0005

Data Index: 189551 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0329. Min Act: -0.0005

Data Index: 384403 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0301. Min Act: -0.0005

Data Index: 846233 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0252. Min Act: -0.0005

Data Index: 373696 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0295. Min Act: -0.0005

Data Index: 156684 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0293. Min Act: -0.0005

Data Index: 770171 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0285. Min Act: -0.0005

Data Index: 904876 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0297. Min Act: -0.0005

Data Index: 510964 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0286. Min Act: -0.0005

Data Index: 106412 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0296. Min Act: -0.0005

Data Index: 1036517 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0264. Min Act: -0.0005

Data Index: 469546 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0289. Min Act: -0.0005

Data Index: 55338 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0282. Min Act: -0.0005

Data Index: 912804 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0300. Min Act: -0.0005

Data Index: 584092 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0287. Min Act: -0.0005

Data Index: 8350 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0265. Min Act: -0.0005

Data Index: 529626 (C4 (Web Text))

Max Activating Token Index: 462