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

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

Neuron 627 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.6532. Min Act: -0.0000

Data Index: 839455 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.7076. Min Act: -0.0000

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.6614. Min Act: -0.0000

Data Index: 316048 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.5086. Min Act: -0.0000

Data Index: 1170988 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.3314. Min Act: -0.0000

Data Index: 1008568 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.1885. Min Act: -0.0000

Data Index: 867605 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.1183. Min Act: -0.0000

Data Index: 435748 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.3297. Min Act: -0.0000

Data Index: 76899 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0794. Min Act: -0.0000

Data Index: 418510 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.9578. Min Act: -0.0000

Data Index: 1192758 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 2.7076. Min Range: -2.7076

Max Act: 2.0524. Min Act: -0.0000

Data Index: 1104424 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.9678. Min Act: -0.0000

Data Index: 544708 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1009114 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.8447. Min Act: -0.0000

Data Index: 1122603 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.8913. Min Act: -0.0000

Data Index: 1025179 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.8935. Min Act: -0.0000

Data Index: 911322 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.9849. Min Act: -0.0000

Data Index: 1221111 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.8600. Min Act: -0.0000

Data Index: 454378 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1175433 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 2.7076. Min Range: -2.7076

Max Act: 1.9287. Min Act: -0.0000

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 84