Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 448 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0321. Min Act: -0.0006

Data Index: 330706 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0006

Data Index: 801792 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1305448 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0301. Min Act: -0.0006

Data Index: 863307 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0308. Min Act: -0.0006

Data Index: 647894 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1285178 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0284. Min Act: -0.0006

Data Index: 889405 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0297. Min Act: -0.0006

Data Index: 764965 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0297. Min Act: -0.0006

Data Index: 646528 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1153891 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0291. Min Act: -0.0006

Data Index: 769141 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0291. Min Act: -0.0006

Data Index: 935994 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0284. Min Act: -0.0006

Data Index: 684918 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1322043 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0272. Min Act: -0.0006

Data Index: 753125 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0282. Min Act: -0.0006

Data Index: 353215 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0281. Min Act: -0.0006

Data Index: 462478 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0275. Min Act: -0.0006

Data Index: 815532 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0278. Min Act: -0.0006

Data Index: 300058 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0269. Min Act: -0.0006

Data Index: 681698 (C4 (Web Text))

Max Activating Token Index: 716