Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2845. Min Act: -0.0002

Data Index: 831901 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.4077. Min Act: -0.0002

Data Index: 703999 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2265. Min Act: -0.0002

Data Index: 320064 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3802. Min Act: -0.0002

Data Index: 691093 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2753. Min Act: -0.0002

Data Index: 365649 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3760. Min Act: -0.0002

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1925. Min Act: -0.0002

Data Index: 103224 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3529. Min Act: -0.0002

Data Index: 1344629 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1272. Min Act: -0.0002

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3208. Min Act: -0.0002

Data Index: 1028742 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2809. Min Act: -0.0002

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1842. Min Act: -0.0002

Data Index: 1004057 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.0671. Min Act: -0.0002

Data Index: 1139066 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.0372. Min Act: -0.0002

Data Index: 54338 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2456. Min Act: -0.0002

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.2232. Min Act: -0.0002

Data Index: 1261041 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.1003. Min Act: -0.0002

Data Index: 445919 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.4077. Min Range: -1.4077

Max Act: 0.9813. Min Act: -0.0002

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.4077. Min Range: -1.4077

Max Act: 1.3262. Min Act: -0.0002

Data Index: 574229 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.4077. Min Range: -1.4077

Max Act: 0.9892. Min Act: -0.0002

Data Index: 1052456 (C4 (Web Text))

Max Activating Token Index: 810