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

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

Neuron 346 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1248415 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.7197. Min Act: -0.0000

Data Index: 733457 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.7068. Min Act: -0.0000

Data Index: 128364 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6316. Min Act: -0.0000

Data Index: 157497 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1331798 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5769. Min Act: -0.0000

Data Index: 458479 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5213. Min Act: -0.0000

Data Index: 389442 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1142042 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5914. Min Act: -0.0000

Data Index: 935488 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5461. Min Act: -0.0001

Data Index: 1099709 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5089. Min Act: -0.0000

Data Index: 859426 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5262. Min Act: -0.0000

Data Index: 671185 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1301432 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1140100 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5149. Min Act: -0.0000

Data Index: 624959 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5177. Min Act: -0.0000

Data Index: 732027 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5289. Min Act: -0.0000

Data Index: 223172 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5103. Min Act: -0.0000

Data Index: 2561 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4809. Min Act: -0.0000

Data Index: 804590 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1075199 (C4 (Web Text))

Max Activating Token Index: 149