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

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

Neuron 879 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: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0001

Data Index: 327349 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8239. Min Act: -0.0001

Data Index: 598024 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7847. Min Act: -0.0000

Data Index: 242661 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1250869 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7988. Min Act: -0.0001

Data Index: 574092 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8194. Min Act: -0.0000

Data Index: 832533 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8190. Min Act: -0.0000

Data Index: 899383 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7785. Min Act: -0.0001

Data Index: 194759 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7510. Min Act: -0.0001

Data Index: 351512 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7446. Min Act: -0.0001

Data Index: 54035 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7584. Min Act: -0.0000

Data Index: 73118 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1065157 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7556. Min Act: -0.0001

Data Index: 244259 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7351. Min Act: -0.0000

Data Index: 267677 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7255. Min Act: -0.0001

Data Index: 668286 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7412. Min Act: -0.0001

Data Index: 668945 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7445. Min Act: -0.0000

Data Index: 67650 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7158. Min Act: -0.0001

Data Index: 303181 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7098. Min Act: -0.0001

Data Index: 48270 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7279. Min Act: -0.0001

Data Index: 363861 (C4 (Web Text))

Max Activating Token Index: 359