Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 280 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.7696. Min Act: -0.0003

Data Index: 251992 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.2798. Min Act: -0.0003

Data Index: 926215 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.2623. Min Act: -0.0003

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.2356. Min Act: -0.0002

Data Index: 964817 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.3164. Min Act: -0.0002

Data Index: 717699 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.2257. Min Act: -0.0003

Data Index: 923499 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.2224. Min Act: -0.0002

Data Index: 507488 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.1177. Min Act: -0.0002

Data Index: 801600 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.1199. Min Act: -0.0002

Data Index: 216704 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.0818. Min Act: -0.0003

Data Index: 658488 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.1279. Min Act: -0.0003

Data Index: 1320477 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.0673. Min Act: -0.0003

Data Index: 153057 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.7696. Min Range: -1.7696

Max Act: 0.9890. Min Act: -0.0003

Data Index: 616070 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.7696. Min Range: -1.7696

Max Act: 0.9540. Min Act: -0.0003

Data Index: 1174067 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.0100. Min Act: -0.0003

Data Index: 214375 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 1.7696. Min Range: -1.7696

Max Act: 1.0365. Min Act: -0.0003

Data Index: 464168 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 1.7696. Min Range: -1.7696

Max Act: 0.9716. Min Act: -0.0003

Data Index: 733042 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.7696. Min Range: -1.7696

Max Act: 0.9276. Min Act: -0.0003

Data Index: 668113 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.7696. Min Range: -1.7696

Max Act: 0.9715. Min Act: -0.0003

Data Index: 273861 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.7696. Min Range: -1.7696

Max Act: 0.8401. Min Act: -0.0003

Data Index: 995046 (C4 (Web Text))

Max Activating Token Index: 575