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

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

Neuron 3770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1016903 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0497. Min Act: -0.0002

Data Index: 934580 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0440. Min Act: -0.0002

Data Index: 288763 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0459. Min Act: -0.0002

Data Index: 411367 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1079597 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0002

Data Index: 849903 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1139625 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0428. Min Act: -0.0002

Data Index: 544975 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1005657 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0376. Min Act: -0.0002

Data Index: 172066 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1193330 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0422. Min Act: -0.0002

Data Index: 793405 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1021084 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0439. Min Act: -0.0002

Data Index: 552335 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0410. Min Act: -0.0002

Data Index: 813634 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1309651 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1180949 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0347. Min Act: -0.0002

Data Index: 494264 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0399. Min Act: -0.0002

Data Index: 203126 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0430. Min Act: -0.0002

Data Index: 329165 (C4 (Web Text))

Max Activating Token Index: 588