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

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

Neuron 3272 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7938. Min Act: -0.0001

Data Index: 478473 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7087. Min Act: -0.0001

Data Index: 244033 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6675. Min Act: -0.0001

Data Index: 902219 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5997. Min Act: -0.0001

Data Index: 933395 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1072723 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6682. Min Act: -0.0001

Data Index: 572134 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6277. Min Act: -0.0001

Data Index: 727077 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6064. Min Act: -0.0001

Data Index: 268262 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6062. Min Act: -0.0001

Data Index: 379662 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6757. Min Act: -0.0001

Data Index: 1037253 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5687. Min Act: -0.0001

Data Index: 1008413 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5431. Min Act: -0.0001

Data Index: 710929 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5831. Min Act: -0.0001

Data Index: 295949 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5812. Min Act: -0.0001

Data Index: 747493 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6735. Min Act: -0.0001

Data Index: 210496 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6101. Min Act: -0.0001

Data Index: 724116 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5927. Min Act: -0.0001

Data Index: 370265 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5667. Min Act: -0.0001

Data Index: 1334198 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6048. Min Act: -0.0001

Data Index: 650184 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.4993. Min Act: -0.0001

Data Index: 894836 (C4 (Web Text))

Max Activating Token Index: 733