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

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

Neuron 1874 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0413. Min Act: -0.0000

Data Index: 253760 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9175. Min Act: -0.0000

Data Index: 324355 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8341. Min Act: -0.0000

Data Index: 573315 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8894. Min Act: -0.0000

Data Index: 444727 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8093. Min Act: -0.0000

Data Index: 760877 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8061. Min Act: -0.0000

Data Index: 274274 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7533. Min Act: -0.0000

Data Index: 734282 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7726. Min Act: -0.0000

Data Index: 15866 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8085. Min Act: -0.0000

Data Index: 370870 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8582. Min Act: -0.0000

Data Index: 267052 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8066. Min Act: -0.0000

Data Index: 819502 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8075. Min Act: -0.0000

Data Index: 640618 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7549. Min Act: -0.0000

Data Index: 246953 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7247. Min Act: -0.0000

Data Index: 156106 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7745. Min Act: -0.0000

Data Index: 246368 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7435. Min Act: -0.0000

Data Index: 596637 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7646. Min Act: -0.0000

Data Index: 153305 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8034. Min Act: -0.0000

Data Index: 721580 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1197844 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7334. Min Act: -0.0000

Data Index: 80962 (C4 (Web Text))

Max Activating Token Index: 27