Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1577 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.5278. Min Act: -0.0000

Data Index: 7025 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3562. Min Act: -0.0000

Data Index: 386637 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1043198 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3004. Min Act: -0.0001

Data Index: 162928 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3006. Min Act: -0.0000

Data Index: 622805 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3010. Min Act: -0.0000

Data Index: 210101 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2842. Min Act: -0.0000

Data Index: 201784 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2992. Min Act: -0.0000

Data Index: 201865 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2750. Min Act: -0.0000

Data Index: 352931 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1470089 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1105112 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2685. Min Act: -0.0000

Data Index: 658178 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2687. Min Act: -0.0000

Data Index: 50074 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2755. Min Act: -0.0000

Data Index: 209621 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2831. Min Act: -0.0000

Data Index: 819717 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1025309 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1198396 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2689. Min Act: -0.0001

Data Index: 1400450 (Python Code)

Max Activating Token Index: 507

Text #18

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2517. Min Act: -0.0001

Data Index: 823006 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.2763. Min Act: -0.0000

Data Index: 103507 (C4 (Web Text))

Max Activating Token Index: 80