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

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

Neuron 2788 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: 0.4061. Min Range: -0.4061

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1357145 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.4061. Min Act: -0.0000

Data Index: 406516 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3879. Min Act: -0.0000

Data Index: 293809 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3642. Min Act: -0.0000

Data Index: 124712 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3031. Min Act: -0.0000

Data Index: 264412 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1151290 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2682. Min Act: -0.0001

Data Index: 853982 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1039195 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1119134 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2582. Min Act: -0.0000

Data Index: 266572 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2675. Min Act: -0.0000

Data Index: 650151 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2410. Min Act: -0.0001

Data Index: 883353 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1010933 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2414. Min Act: -0.0000

Data Index: 919799 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1109695 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2502. Min Act: -0.0001

Data Index: 616412 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2447. Min Act: -0.0000

Data Index: 160408 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2258. Min Act: -0.0000

Data Index: 385543 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2306. Min Act: -0.0000

Data Index: 604687 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.4061. Min Range: -0.4061

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1266037 (C4 (Web Text))

Max Activating Token Index: 188