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

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

Neuron 1963 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3554. Min Act: -0.0001

Data Index: 810875 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3622. Min Act: -0.0000

Data Index: 676757 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3599. Min Act: -0.0001

Data Index: 1148622 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3454. Min Act: -0.0000

Data Index: 298900 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3551. Min Act: -0.0000

Data Index: 952906 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3298. Min Act: -0.0000

Data Index: 860645 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3624. Min Act: -0.0000

Data Index: 192836 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3304. Min Act: -0.0000

Data Index: 939870 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3277. Min Act: -0.0000

Data Index: 355466 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3047. Min Act: -0.0000

Data Index: 113661 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3264. Min Act: -0.0000

Data Index: 713734 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1337084 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2887. Min Act: -0.0000

Data Index: 25325 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3173. Min Act: -0.0000

Data Index: 231272 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2925. Min Act: -0.0000

Data Index: 937756 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3028. Min Act: -0.0000

Data Index: 272581 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3021. Min Act: -0.0000

Data Index: 530975 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3111. Min Act: -0.0000

Data Index: 27081 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2902. Min Act: -0.0000

Data Index: 586500 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2876. Min Act: -0.0000

Data Index: 747730 (C4 (Web Text))

Max Activating Token Index: 70