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

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

Neuron 3566 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: 0.4895. Min Range: -0.4895

Max Act: 0.4895. Min Act: -0.0000

Data Index: 631947 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4601. Min Act: -0.0000

Data Index: 803890 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1222527 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4414. Min Act: -0.0000

Data Index: 530982 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4567. Min Act: -0.0000

Data Index: 319987 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4426. Min Act: -0.0000

Data Index: 720120 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4341. Min Act: -0.0000

Data Index: 800070 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1357251 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4088. Min Act: -0.0000

Data Index: 810238 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4176. Min Act: -0.0000

Data Index: 753489 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4168. Min Act: -0.0000

Data Index: 500586 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1042531 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4032. Min Act: -0.0000

Data Index: 452045 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1173908 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3944. Min Act: -0.0000

Data Index: 799397 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3807. Min Act: -0.0000

Data Index: 216730 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1219992 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1249864 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3657. Min Act: -0.0000

Data Index: 145158 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1281618 (C4 (Web Text))

Max Activating Token Index: 286