Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5243 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.6995. Min Act: -0.0000

Data Index: 1043672 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.6994. Min Act: -0.0000

Data Index: 1056163 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.4489. Min Act: -0.0000

Data Index: 1265976 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.4326. Min Act: -0.0000

Data Index: 905971 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.2776. Min Act: -0.0000

Data Index: 431343 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1125. Min Act: -0.0000

Data Index: 540165 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.2182. Min Act: -0.0000

Data Index: 740023 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1953. Min Act: -0.0000

Data Index: 187850 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1841. Min Act: -0.0000

Data Index: 1062907 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1716. Min Act: -0.0000

Data Index: 237443 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1666. Min Act: -0.0000

Data Index: 1213423 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.0507. Min Act: -0.0000

Data Index: 721515 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.2544. Min Act: -0.0000

Data Index: 268704 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.0235. Min Act: -0.0000

Data Index: 643565 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1570. Min Act: -0.0000

Data Index: 167205 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1240. Min Act: -0.0000

Data Index: 63294 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1079. Min Act: -0.0000

Data Index: 1219032 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 2.6995. Min Range: -2.6995

Max Act: 1.9886. Min Act: -0.0000

Data Index: 739364 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 2.6995. Min Range: -2.6995

Max Act: 1.9919. Min Act: -0.0000

Data Index: 955125 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 2.6995. Min Range: -2.6995

Max Act: 2.1996. Min Act: -0.0000

Data Index: 887113 (C4 (Web Text))

Max Activating Token Index: 772