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

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

Neuron 3450 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3572. Min Act: -0.0000

Data Index: 813174 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1648184 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3230. Min Act: 0.0000

Data Index: 1087085 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1241286 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1043700 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2798. Min Act: -0.0000

Data Index: 45554 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2914. Min Act: 0.0000

Data Index: 87750 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2696. Min Act: -0.0000

Data Index: 853136 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2708. Min Act: -0.0000

Data Index: 365518 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2811. Min Act: -0.0000

Data Index: 716696 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2686. Min Act: -0.0000

Data Index: 972898 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2615. Min Act: -0.0000

Data Index: 260657 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2587. Min Act: -0.0000

Data Index: 20655 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2626. Min Act: 0.0000

Data Index: 343727 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2626. Min Act: 0.0000

Data Index: 1293102 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2802. Min Act: -0.0000

Data Index: 540905 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2460. Min Act: -0.0000

Data Index: 534050 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2499. Min Act: 0.0000

Data Index: 989576 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2485. Min Act: -0.0000

Data Index: 725972 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2815. Min Act: -0.0000

Data Index: 99189 (C4 (Web Text))

Max Activating Token Index: 906