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

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

Neuron 3726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2539. Min Range: -4.2539

Max Act: 4.2539. Min Act: -0.0000

Data Index: 507602 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.9380. Min Act: -0.0000

Data Index: 905117 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.8328. Min Act: -0.0000

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.8537. Min Act: -0.0000

Data Index: 892199 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.6184. Min Act: -0.0000

Data Index: 721606 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.3600. Min Act: -0.0000

Data Index: 1317483 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.3659. Min Act: -0.0000

Data Index: 421480 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.2013. Min Act: -0.0000

Data Index: 765686 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 4.2539. Min Range: -4.2539

Max Act: 3.5335. Min Act: -0.0000

Data Index: 451364 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.9865. Min Act: -0.0000

Data Index: 741731 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.8223. Min Act: -0.0000

Data Index: 620813 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.9543. Min Act: -0.0000

Data Index: 858026 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.7981. Min Act: -0.0000

Data Index: 1184186 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.6296. Min Act: -0.0000

Data Index: 887984 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.7665. Min Act: -0.0000

Data Index: 1104071 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.6665. Min Act: -0.0000

Data Index: 838358 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.6500. Min Act: -0.0000

Data Index: 1334780 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.5086. Min Act: -0.0000

Data Index: 812804 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.5068. Min Act: -0.0000

Data Index: 18523 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 4.2539. Min Range: -4.2539

Max Act: 2.4723. Min Act: -0.0000

Data Index: 788491 (C4 (Web Text))

Max Activating Token Index: 1001