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

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

Neuron 3956 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7897. Min Range: -5.7897

Max Act: 5.7897. Min Act: -0.0000

Data Index: 931610 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.8821. Min Act: -0.0000

Data Index: 1055212 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.5205. Min Act: -0.0000

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 5.7897. Min Range: -5.7897

Max Act: 5.0472. Min Act: -0.0000

Data Index: 1035280 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.7760. Min Act: -0.0000

Data Index: 1061974 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.1378. Min Act: -0.0000

Data Index: 1100035 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.7561. Min Act: -0.0000

Data Index: 496009 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.7047. Min Act: -0.0000

Data Index: 565134 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.7954. Min Act: -0.0000

Data Index: 1036669 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.5076. Min Act: -0.0000

Data Index: 538499 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.3115. Min Act: -0.0000

Data Index: 109456 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.1837. Min Act: -0.0000

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.1167. Min Act: -0.0000

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 5.7897. Min Range: -5.7897

Max Act: 3.9465. Min Act: -0.0000

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.3011. Min Act: -0.0000

Data Index: 1122093 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.1040. Min Act: -0.0001

Data Index: 1323998 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.1305. Min Act: -0.0001

Data Index: 1186789 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.1792. Min Act: -0.0000

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 5.7897. Min Range: -5.7897

Max Act: 4.0067. Min Act: -0.0001

Data Index: 848809 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 5.7897. Min Range: -5.7897

Max Act: 3.6659. Min Act: -0.0000

Data Index: 350955 (C4 (Web Text))

Max Activating Token Index: 370