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

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

Neuron 2312 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5831. Min Act: -0.0002

Data Index: 8403 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5785. Min Act: -0.0002

Data Index: 535810 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5658. Min Act: -0.0002

Data Index: 859878 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5755. Min Act: -0.0002

Data Index: 907040 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5551. Min Act: -0.0002

Data Index: 1226658 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5639. Min Act: -0.0002

Data Index: 354088 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5447. Min Act: -0.0002

Data Index: 139146 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5531. Min Act: -0.0002

Data Index: 569679 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5352. Min Act: -0.0002

Data Index: 436623 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5292. Min Act: -0.0002

Data Index: 913000 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5328. Min Act: -0.0002

Data Index: 397206 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5355. Min Act: -0.0002

Data Index: 699088 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5407. Min Act: -0.0002

Data Index: 193803 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5254. Min Act: -0.0002

Data Index: 529995 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5310. Min Act: -0.0002

Data Index: 791289 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5220. Min Act: -0.0002

Data Index: 1207385 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5187. Min Act: -0.0002

Data Index: 117412 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5269. Min Act: -0.0002

Data Index: 630260 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5228. Min Act: -0.0002

Data Index: 602623 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.5831. Min Range: -0.5831

Max Act: 0.5196. Min Act: -0.0003

Data Index: 208170 (C4 (Web Text))

Max Activating Token Index: 524