Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0002

Data Index: 548752 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1057116 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0320. Min Act: -0.0001

Data Index: 965907 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0327. Min Act: -0.0002

Data Index: 798054 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1400416 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0325. Min Act: -0.0002

Data Index: 287578 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0307. Min Act: -0.0001

Data Index: 976292 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0280. Min Act: -0.0002

Data Index: 571426 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1128968 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0327. Min Act: -0.0001

Data Index: 367770 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0289. Min Act: -0.0001

Data Index: 361908 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1253021 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0282. Min Act: -0.0002

Data Index: 972146 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0296. Min Act: -0.0002

Data Index: 113255 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0295. Min Act: -0.0001

Data Index: 350834 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0292. Min Act: -0.0001

Data Index: 114842 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0281. Min Act: -0.0002

Data Index: 971914 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1122553 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0281. Min Act: -0.0001

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1076647 (C4 (Web Text))

Max Activating Token Index: 76