Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4482 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6737. Min Act: -0.0000

Data Index: 1135802 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.7897. Min Act: -0.0000

Data Index: 800747 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.3359. Min Act: -0.0000

Data Index: 946667 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.3468. Min Act: -0.0000

Data Index: 1137924 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.2930. Min Act: -0.0000

Data Index: 184469 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.4391. Min Act: -0.0000

Data Index: 348082 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.0872. Min Act: -0.0000

Data Index: 659023 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.2369. Min Act: -0.0000

Data Index: 972252 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.2180. Min Act: -0.0000

Data Index: 710279 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.2009. Min Act: -0.0000

Data Index: 31092 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.0104. Min Act: -0.0000

Data Index: 334071 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 3.7897. Min Range: -3.7897

Max Act: 2.9958. Min Act: -0.0000

Data Index: 1141983 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.1086. Min Act: -0.0000

Data Index: 318705 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 3.7897. Min Range: -3.7897

Max Act: 2.9394. Min Act: -0.0000

Data Index: 75452 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.0878. Min Act: -0.0000

Data Index: 345685 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.0918. Min Act: -0.0000

Data Index: 1069530 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.0282. Min Act: -0.0000

Data Index: 369802 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.0316. Min Act: -0.0000

Data Index: 407870 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.0311. Min Act: -0.0000

Data Index: 952490 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 3.7897. Min Range: -3.7897

Max Act: 2.7579. Min Act: -0.0000

Data Index: 1061671 (C4 (Web Text))

Max Activating Token Index: 741