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

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

Neuron 1329 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1335423 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4467. Min Act: -0.0000

Data Index: 459535 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1166969 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.4097. Min Act: -0.0000

Data Index: 16369 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3897. Min Act: 0.0003

Data Index: 451894 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3936. Min Act: -0.0000

Data Index: 337477 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3654. Min Act: -0.0000

Data Index: 853483 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3508. Min Act: -0.0000

Data Index: 513661 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1099902 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3472. Min Act: -0.0000

Data Index: 889350 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3269. Min Act: 0.0000

Data Index: 1029885 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3132. Min Act: -0.0000

Data Index: 427505 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3254. Min Act: -0.0000

Data Index: 387435 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3199. Min Act: -0.0000

Data Index: 216085 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3216. Min Act: 0.0002

Data Index: 333723 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3146. Min Act: -0.0000

Data Index: 943491 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3183. Min Act: -0.0000

Data Index: 133402 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3013. Min Act: 0.0000

Data Index: 88562 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3049. Min Act: 0.0000

Data Index: 235418 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.4467. Min Range: -0.4467

Max Act: 0.3054. Min Act: 0.0000

Data Index: 276875 (C4 (Web Text))

Max Activating Token Index: 89