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

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

Neuron 161 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4684. Min Range: -2.4684

Max Act: 2.4684. Min Act: -0.0000

Data Index: 581507 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 2.4684. Min Range: -2.4684

Max Act: 2.3954. Min Act: -0.0000

Data Index: 1296063 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 2.4684. Min Range: -2.4684

Max Act: 2.0638. Min Act: -0.0000

Data Index: 730371 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 2.4684. Min Range: -2.4684

Max Act: 2.0486. Min Act: -0.0000

Data Index: 27542 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 2.4684. Min Range: -2.4684

Max Act: 2.0007. Min Act: -0.0000

Data Index: 846857 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.8005. Min Act: -0.0000

Data Index: 671273 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6976. Min Act: -0.0000

Data Index: 680801 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.7779. Min Act: -0.0000

Data Index: 1060453 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.7100. Min Act: -0.0000

Data Index: 35878 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.7037. Min Act: -0.0000

Data Index: 1046614 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.7885. Min Act: -0.0000

Data Index: 104225 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1164558 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6831. Min Act: -0.0000

Data Index: 1292319 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.8056. Min Act: -0.0000

Data Index: 537229 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1343649 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6700. Min Act: -0.0000

Data Index: 210776 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6443. Min Act: -0.0000

Data Index: 461540 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1328340 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1153277 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 2.4684. Min Range: -2.4684

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1616636 (Python Code)

Max Activating Token Index: 1017