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

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

Neuron 5929 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0748. Min Range: -5.0748

Max Act: 5.0748. Min Act: -0.0000

Data Index: 145744 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.4547. Min Act: -0.0000

Data Index: 79950 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.6057. Min Act: -0.0000

Data Index: 102912 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.3813. Min Act: -0.0000

Data Index: 906377 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.2566. Min Act: -0.0000

Data Index: 972734 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.9517. Min Act: -0.0000

Data Index: 904714 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.2335. Min Act: -0.0000

Data Index: 373650 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.9109. Min Act: -0.0000

Data Index: 1003207 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.6972. Min Act: -0.0000

Data Index: 136066 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.4910. Min Act: -0.0000

Data Index: 1182925 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.8473. Min Act: -0.0000

Data Index: 446696 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.6674. Min Act: -0.0000

Data Index: 696963 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.8064. Min Act: -0.0000

Data Index: 259715 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.7905. Min Act: -0.0000

Data Index: 286449 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.7239. Min Act: -0.0000

Data Index: 1189908 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.7056. Min Act: -0.0000

Data Index: 987697 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.6536. Min Act: -0.0000

Data Index: 1218573 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.6105. Min Act: -0.0000

Data Index: 1100142 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.6418. Min Act: -0.0000

Data Index: 803647 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.6157. Min Act: -0.0000

Data Index: 1200960 (C4 (Web Text))

Max Activating Token Index: 835