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

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

Neuron 3327 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2591. Min Act: -0.0000

Data Index: 938370 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2441. Min Act: -0.0001

Data Index: 1617968 (Python Code)

Max Activating Token Index: 684

Text #2

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1136456 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2088. Min Act: -0.0001

Data Index: 359702 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1918. Min Act: -0.0001

Data Index: 204914 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2216. Min Act: -0.0001

Data Index: 1158510 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1902. Min Act: -0.0000

Data Index: 999399 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1574505 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2024. Min Act: -0.0001

Data Index: 1475106 (Python Code)

Max Activating Token Index: 476

Text #9

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1977. Min Act: -0.0001

Data Index: 78435 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2146. Min Act: -0.0000

Data Index: 247281 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2058. Min Act: -0.0001

Data Index: 826677 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1474193 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1478665 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2117. Min Act: -0.0001

Data Index: 793227 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.2107. Min Act: -0.0001

Data Index: 172886 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1890. Min Act: -0.0000

Data Index: 785432 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1470421 (Python Code)

Max Activating Token Index: 470

Text #18

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1940. Min Act: -0.0001

Data Index: 860603 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.2591. Min Range: -0.2591

Max Act: 0.1813. Min Act: -0.0000

Data Index: 605436 (C4 (Web Text))

Max Activating Token Index: 322