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

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

Neuron 398 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: 0.0347. Min Range: -0.0347

Max Act: 0.0347. Min Act: -0.0006

Data Index: 876887 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0339. Min Act: -0.0006

Data Index: 84440 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0336. Min Act: -0.0006

Data Index: 1140593 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0330. Min Act: -0.0006

Data Index: 424056 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0309. Min Act: -0.0006

Data Index: 92122 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0291. Min Act: -0.0006

Data Index: 14697 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0294. Min Act: -0.0006

Data Index: 865602 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0299. Min Act: -0.0006

Data Index: 202468 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1010887 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0287. Min Act: -0.0006

Data Index: 469782 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0293. Min Act: -0.0006

Data Index: 89958 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0285. Min Act: -0.0006

Data Index: 692552 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0297. Min Act: -0.0006

Data Index: 451159 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0296. Min Act: -0.0006

Data Index: 93483 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0282. Min Act: -0.0006

Data Index: 342536 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1317976 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1222661 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1214486 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0271. Min Act: -0.0006

Data Index: 395329 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0284. Min Act: -0.0006

Data Index: 864708 (C4 (Web Text))

Max Activating Token Index: 19