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

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

Neuron 1376 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0006

Data Index: 856947 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0394. Min Act: -0.0006

Data Index: 26536 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0368. Min Act: -0.0006

Data Index: 431510 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1337750 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0337. Min Act: -0.0006

Data Index: 75186 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1001768 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0345. Min Act: -0.0006

Data Index: 1307166 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1145895 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0360. Min Act: -0.0006

Data Index: 1094884 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1294818 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1131299 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1176317 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1087354 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0330. Min Act: -0.0006

Data Index: 230781 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1236491 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0306. Min Act: -0.0006

Data Index: 328299 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0326. Min Act: -0.0006

Data Index: 732444 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1144076 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0329. Min Act: -0.0006

Data Index: 485528 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1178452 (C4 (Web Text))

Max Activating Token Index: 660