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

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

Neuron 3750 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 139120 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1250273 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1273649 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3088. Min Act: -0.0000

Data Index: 974054 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3043. Min Act: -0.0000

Data Index: 119163 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2861. Min Act: -0.0000

Data Index: 231822 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2772. Min Act: -0.0000

Data Index: 809044 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2859. Min Act: -0.0000

Data Index: 266195 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2602. Min Act: -0.0000

Data Index: 531772 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2812. Min Act: -0.0000

Data Index: 185760 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2827. Min Act: -0.0000

Data Index: 477862 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2793. Min Act: -0.0000

Data Index: 636563 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2823. Min Act: -0.0000

Data Index: 886145 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2639. Min Act: -0.0000

Data Index: 392277 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2676. Min Act: -0.0000

Data Index: 429176 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1333293 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1029598 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1067188 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2690. Min Act: -0.0000

Data Index: 980046 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2681. Min Act: -0.0000

Data Index: 577186 (C4 (Web Text))

Max Activating Token Index: 182