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

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

Neuron 4235 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8045. Min Act: -0.0000

Data Index: 78150 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7553. Min Act: -0.0000

Data Index: 120653 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1175638 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7277. Min Act: 0.0000

Data Index: 410691 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7302. Min Act: -0.0000

Data Index: 913257 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5870. Min Act: -0.0000

Data Index: 846984 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6056. Min Act: -0.0000

Data Index: 476413 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1121588 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5951. Min Act: -0.0000

Data Index: 322216 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5636. Min Act: -0.0000

Data Index: 146448 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5849. Min Act: -0.0000

Data Index: 775664 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5448. Min Act: -0.0000

Data Index: 662590 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1208435 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5095. Min Act: -0.0000

Data Index: 390585 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5108. Min Act: -0.0000

Data Index: 524256 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5059. Min Act: -0.0000

Data Index: 57644 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1061461 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1180986 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1294702 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4601. Min Act: -0.0000

Data Index: 345408 (C4 (Web Text))

Max Activating Token Index: 453