Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4068 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4181. Min Act: -0.0000

Data Index: 661080 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4189. Min Act: -0.0001

Data Index: 631469 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4275. Min Act: -0.0001

Data Index: 442847 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1291479 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1181476 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3976. Min Act: -0.0001

Data Index: 1205265 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3533. Min Act: -0.0001

Data Index: 558189 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3336. Min Act: -0.0001

Data Index: 192258 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1037613 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3785. Min Act: -0.0001

Data Index: 921309 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3181. Min Act: -0.0001

Data Index: 893260 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3270. Min Act: -0.0000

Data Index: 429319 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1236737 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3024. Min Act: -0.0001

Data Index: 1069964 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3101. Min Act: -0.0001

Data Index: 17304 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3367. Min Act: -0.0000

Data Index: 517467 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3385. Min Act: -0.0001

Data Index: 951210 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3280. Min Act: -0.0001

Data Index: 1357482 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3152. Min Act: -0.0000

Data Index: 204850 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1325798 (C4 (Web Text))

Max Activating Token Index: 686