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

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

Neuron 4260 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.6830. Min Act: -0.0000

Data Index: 912749 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.5861. Min Act: -0.0000

Data Index: 413615 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.4493. Min Act: -0.0000

Data Index: 506463 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.4045. Min Act: -0.0000

Data Index: 202558 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.3361. Min Act: -0.0000

Data Index: 597593 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.1044. Min Act: -0.0000

Data Index: 924406 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.1037. Min Act: -0.0000

Data Index: 681274 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.0291. Min Act: -0.0000

Data Index: 1124303 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.9731. Min Act: -0.0000

Data Index: 1175760 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 4.6830. Min Range: -4.6830

Max Act: 4.0721. Min Act: -0.0000

Data Index: 47392 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.8610. Min Act: -0.0000

Data Index: 600224 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.7586. Min Act: -0.0000

Data Index: 1187754 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.3264. Min Act: -0.0000

Data Index: 853324 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.9015. Min Act: -0.0000

Data Index: 5863 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.5610. Min Act: -0.0000

Data Index: 1021658 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.5159. Min Act: -0.0000

Data Index: 773958 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.3445. Min Act: -0.0000

Data Index: 370449 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.4334. Min Act: -0.0000

Data Index: 992005 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.4654. Min Act: -0.0000

Data Index: 1134318 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 4.6830. Min Range: -4.6830

Max Act: 3.5083. Min Act: -0.0000

Data Index: 5429 (C4 (Web Text))

Max Activating Token Index: 403