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

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

Neuron 2357 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: 0.7597. Min Range: -0.7597

Max Act: 0.7597. Min Act: -0.0000

Data Index: 285327 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7427. Min Act: -0.0000

Data Index: 90175 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7059. Min Act: -0.0000

Data Index: 192064 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1151815 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7077. Min Act: -0.0000

Data Index: 484992 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6595. Min Act: -0.0000

Data Index: 695498 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6755. Min Act: -0.0000

Data Index: 43259 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6502. Min Act: -0.0000

Data Index: 76900 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6090. Min Act: -0.0000

Data Index: 889378 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1197424 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6024. Min Act: -0.0000

Data Index: 867925 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1023799 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5919. Min Act: -0.0000

Data Index: 650297 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.6369. Min Act: -0.0000

Data Index: 330852 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5799. Min Act: -0.0000

Data Index: 601252 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1103876 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5672. Min Act: -0.0000

Data Index: 520908 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5982. Min Act: -0.0000

Data Index: 667611 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5753. Min Act: -0.0000

Data Index: 732567 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1344311 (C4 (Web Text))

Max Activating Token Index: 595