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

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

Neuron 4252 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.5588. Min Act: 0.0000

Data Index: 1135937 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.2216. Min Act: -0.0000

Data Index: 774496 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.2905. Min Act: 0.0000

Data Index: 317332 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.2046. Min Act: -0.0000

Data Index: 1192596 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.0319. Min Act: -0.0000

Data Index: 455253 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.1401. Min Act: -0.0000

Data Index: 104695 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.0879. Min Act: -0.0000

Data Index: 441364 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.9620. Min Act: -0.0000

Data Index: 613362 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.0493. Min Act: -0.0000

Data Index: 457009 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.8734. Min Act: -0.0000

Data Index: 1062720 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1324483 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 2.5588. Min Range: -2.5588

Max Act: 2.0856. Min Act: -0.0000

Data Index: 505257 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.8351. Min Act: -0.0000

Data Index: 163858 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.9383. Min Act: -0.0000

Data Index: 81658 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.8310. Min Act: -0.0000

Data Index: 274921 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.8250. Min Act: -0.0000

Data Index: 717245 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.8051. Min Act: -0.0000

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.7893. Min Act: -0.0000

Data Index: 1304869 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.8957. Min Act: -0.0000

Data Index: 877081 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 2.5588. Min Range: -2.5588

Max Act: 1.7923. Min Act: -0.0000

Data Index: 1124874 (C4 (Web Text))

Max Activating Token Index: 179