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

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

Neuron 3089 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0854. Min Range: -1.0854

Max Act: 1.0854. Min Act: -0.0000

Data Index: 309344 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.0854. Min Range: -1.0854

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1047907 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 1.0854. Min Range: -1.0854

Max Act: 1.0152. Min Act: -0.0000

Data Index: 787509 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.9493. Min Act: -0.0000

Data Index: 416884 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1058704 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1247748 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1278650 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7714. Min Act: -0.0000

Data Index: 764438 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7260. Min Act: -0.0000

Data Index: 587314 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7563. Min Act: -0.0000

Data Index: 107570 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7502. Min Act: -0.0000

Data Index: 505548 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.7450. Min Act: -0.0000

Data Index: 642635 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6983. Min Act: -0.0000

Data Index: 336804 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6794. Min Act: -0.0000

Data Index: 64201 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6923. Min Act: -0.0000

Data Index: 5033 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1356477 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6706. Min Act: -0.0000

Data Index: 526923 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6288. Min Act: -0.0000

Data Index: 953082 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1051899 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.0854. Min Range: -1.0854

Max Act: 0.6180. Min Act: -0.0000

Data Index: 231510 (C4 (Web Text))

Max Activating Token Index: 620