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

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

Neuron 367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0044. Min Range: -2.0044

Max Act: 2.0044. Min Act: -0.0000

Data Index: 314836 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1330931 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.7158. Min Act: -0.0000

Data Index: 464554 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.6011. Min Act: -0.0000

Data Index: 1213585 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.5609. Min Act: -0.0000

Data Index: 768037 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.5456. Min Act: -0.0000

Data Index: 58409 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.5407. Min Act: -0.0000

Data Index: 927195 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.5192. Min Act: -0.0000

Data Index: 587995 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.5062. Min Act: -0.0000

Data Index: 333065 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.4964. Min Act: -0.0000

Data Index: 558857 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.3872. Min Act: -0.0000

Data Index: 283032 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.3037. Min Act: -0.0000

Data Index: 359970 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.4175. Min Act: -0.0000

Data Index: 1232998 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1166638 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.4585. Min Act: -0.0000

Data Index: 92309 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1158560 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.2697. Min Act: -0.0000

Data Index: 833351 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.3423. Min Act: -0.0000

Data Index: 828232 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.3391. Min Act: -0.0000

Data Index: 344154 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 2.0044. Min Range: -2.0044

Max Act: 1.3392. Min Act: -0.0000

Data Index: 1107670 (C4 (Web Text))

Max Activating Token Index: 628