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

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

Neuron 83 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8829. Min Act: -0.0001

Data Index: 535345 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8622. Min Act: -0.0000

Data Index: 68526 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1075280 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6871. Min Act: -0.0000

Data Index: 217221 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1257005 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6943. Min Act: -0.0000

Data Index: 435091 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7048. Min Act: -0.0000

Data Index: 44695 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6394. Min Act: -0.0000

Data Index: 691898 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6351. Min Act: -0.0000

Data Index: 605732 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6716. Min Act: -0.0000

Data Index: 769240 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6240. Min Act: -0.0000

Data Index: 430665 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6417. Min Act: -0.0001

Data Index: 873894 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6174. Min Act: -0.0000

Data Index: 6487 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6340. Min Act: -0.0000

Data Index: 179218 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6336. Min Act: -0.0001

Data Index: 146435 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6261. Min Act: -0.0000

Data Index: 672165 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6305. Min Act: -0.0000

Data Index: 286577 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6035. Min Act: -0.0000

Data Index: 242652 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6240. Min Act: -0.0001

Data Index: 302691 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5947. Min Act: -0.0001

Data Index: 1110687 (C4 (Web Text))

Max Activating Token Index: 354