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

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

Neuron 2692 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0001

Data Index: 605990 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0454. Min Act: -0.0001

Data Index: 243938 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0482. Min Act: -0.0000

Data Index: 824629 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0459. Min Act: -0.0001

Data Index: 491827 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0370. Min Act: -0.0001

Data Index: 899721 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0468. Min Act: -0.0001

Data Index: 288153 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1233260 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1119850 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0415. Min Act: -0.0001

Data Index: 496303 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1055154 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1182392 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1115421 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1247267 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0401. Min Act: -0.0001

Data Index: 660223 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0402. Min Act: -0.0001

Data Index: 560957 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1161898 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0363. Min Act: -0.0001

Data Index: 384573 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0379. Min Act: -0.0001

Data Index: 510665 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1009967 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0378. Min Act: -0.0000

Data Index: 448231 (C4 (Web Text))

Max Activating Token Index: 15