Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 72 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1158758 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1187899 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1236806 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0309. Min Act: -0.0004

Data Index: 1013455 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0298. Min Act: -0.0005

Data Index: 934495 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0303. Min Act: -0.0004

Data Index: 1173875 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0304. Min Act: -0.0004

Data Index: 113434 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0303. Min Act: -0.0004

Data Index: 112135 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0292. Min Act: -0.0005

Data Index: 102512 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0296. Min Act: -0.0004

Data Index: 256944 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0296. Min Act: -0.0004

Data Index: 44677 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0296. Min Act: -0.0004

Data Index: 136099 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0288. Min Act: -0.0004

Data Index: 205745 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0293. Min Act: -0.0004

Data Index: 269600 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0292. Min Act: -0.0005

Data Index: 1138987 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0284. Min Act: -0.0004

Data Index: 19213 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0284. Min Act: -0.0005

Data Index: 391930 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0289. Min Act: -0.0004

Data Index: 84611 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0288. Min Act: -0.0004

Data Index: 291925 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0286. Min Act: -0.0004

Data Index: 1006853 (C4 (Web Text))

Max Activating Token Index: 75