Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2074 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.5029. Min Act: -0.0000

Data Index: 636682 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.4325. Min Act: -0.0000

Data Index: 1067623 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.3383. Min Act: -0.0000

Data Index: 1070929 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.0751. Min Act: -0.0000

Data Index: 1147696 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.0708. Min Act: -0.0000

Data Index: 1132554 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.1765. Min Act: -0.0000

Data Index: 884083 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.1583. Min Act: -0.0000

Data Index: 1151365 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.0872. Min Act: -0.0000

Data Index: 316466 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.0928. Min Act: -0.0000

Data Index: 4979 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.0828. Min Act: -0.0000

Data Index: 779553 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.0644. Min Act: -0.0000

Data Index: 256011 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.0194. Min Act: -0.0000

Data Index: 672267 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 2.5029. Min Range: -2.5029

Max Act: 1.9995. Min Act: -0.0000

Data Index: 487453 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 2.5029. Min Range: -2.5029

Max Act: 2.1245. Min Act: -0.0000

Data Index: 1135721 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 2.5029. Min Range: -2.5029

Max Act: 1.9855. Min Act: -0.0000

Data Index: 787422 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 2.5029. Min Range: -2.5029

Max Act: 1.9823. Min Act: -0.0000

Data Index: 1070695 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 2.5029. Min Range: -2.5029

Max Act: 1.9615. Min Act: -0.0000

Data Index: 313875 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 2.5029. Min Range: -2.5029

Max Act: 1.9653. Min Act: -0.0000

Data Index: 1172098 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 2.5029. Min Range: -2.5029

Max Act: 1.9576. Min Act: -0.0000

Data Index: 793748 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 2.5029. Min Range: -2.5029

Max Act: 1.8302. Min Act: -0.0000

Data Index: 1170436 (C4 (Web Text))

Max Activating Token Index: 639