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

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

Neuron 105 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: 0.0373. Min Range: -0.0373

Max Act: 0.0373. Min Act: -0.0006

Data Index: 644454 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1017781 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0314. Min Act: -0.0006

Data Index: 733179 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1229547 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0310. Min Act: -0.0006

Data Index: 7126 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1112254 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0271. Min Act: -0.0006

Data Index: 879725 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0301. Min Act: -0.0006

Data Index: 828417 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0300. Min Act: -0.0006

Data Index: 635230 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0291. Min Act: -0.0006

Data Index: 756295 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0269. Min Act: -0.0006

Data Index: 502955 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0286. Min Act: -0.0006

Data Index: 123650 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1158886 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0297. Min Act: -0.0006

Data Index: 38091 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1096223 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0277. Min Act: -0.0006

Data Index: 253757 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0310. Min Act: -0.0006

Data Index: 571038 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0275. Min Act: -0.0006

Data Index: 764118 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0301. Min Act: -0.0006

Data Index: 46951 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0285. Min Act: -0.0006

Data Index: 55341 (C4 (Web Text))

Max Activating Token Index: 769