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

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

Neuron 4403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0275. Min Range: -4.0275

Max Act: 3.8722. Min Act: -0.0000

Data Index: 1346482 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 4.0275. Min Range: -4.0275

Max Act: 4.0275. Min Act: -0.0000

Data Index: 654924 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 4.0275. Min Range: -4.0275

Max Act: 3.1824. Min Act: -0.0000

Data Index: 325118 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.8854. Min Act: -0.0001

Data Index: 497397 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 4.0275. Min Range: -4.0275

Max Act: 3.1864. Min Act: -0.0000

Data Index: 1245400 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.9228. Min Act: -0.0000

Data Index: 729269 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.8543. Min Act: -0.0000

Data Index: 58988 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.7053. Min Act: -0.0000

Data Index: 775833 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.9256. Min Act: -0.0000

Data Index: 1089150 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 4.0275. Min Range: -4.0275

Max Act: 3.0331. Min Act: -0.0000

Data Index: 385404 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 4.0275. Min Range: -4.0275

Max Act: 3.0112. Min Act: -0.0000

Data Index: 818245 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.8614. Min Act: -0.0000

Data Index: 1145390 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.8578. Min Act: -0.0000

Data Index: 191400 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.8083. Min Act: -0.0000

Data Index: 599627 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.7993. Min Act: -0.0000

Data Index: 695375 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.7863. Min Act: -0.0000

Data Index: 1140329 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.5169. Min Act: -0.0000

Data Index: 720396 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.7524. Min Act: -0.0000

Data Index: 1187185 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.8925. Min Act: -0.0000

Data Index: 674370 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 4.0275. Min Range: -4.0275

Max Act: 2.7445. Min Act: -0.0000

Data Index: 418512 (C4 (Web Text))

Max Activating Token Index: 490