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

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

Neuron 3361 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3139. Min Act: -0.0000

Data Index: 259458 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3119. Min Act: -0.0000

Data Index: 748435 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3087. Min Act: -0.0000

Data Index: 782392 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3059. Min Act: -0.0000

Data Index: 925269 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2952. Min Act: -0.0000

Data Index: 248378 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1010886 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3043. Min Act: -0.0000

Data Index: 307647 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3212. Min Act: -0.0000

Data Index: 462859 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2889. Min Act: -0.0000

Data Index: 498928 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2924. Min Act: -0.0000

Data Index: 484633 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2906. Min Act: -0.0000

Data Index: 13372 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2982. Min Act: -0.0000

Data Index: 628150 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2758. Min Act: -0.0000

Data Index: 275059 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2830. Min Act: -0.0000

Data Index: 340285 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2915. Min Act: -0.0000

Data Index: 161338 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2816. Min Act: -0.0000

Data Index: 277481 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2708. Min Act: -0.0000

Data Index: 3853 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2779. Min Act: -0.0000

Data Index: 619538 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2881. Min Act: -0.0000

Data Index: 362508 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2664. Min Act: -0.0000

Data Index: 741340 (C4 (Web Text))

Max Activating Token Index: 288