Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1430 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0005

Data Index: 728095 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0455. Min Act: -0.0005

Data Index: 946041 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0491. Min Act: -0.0005

Data Index: 1196941 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0451. Min Act: -0.0005

Data Index: 926562 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0448. Min Act: -0.0005

Data Index: 520511 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0445. Min Act: -0.0005

Data Index: 1249099 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0443. Min Act: -0.0005

Data Index: 51884 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0411. Min Act: -0.0005

Data Index: 1164932 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0417. Min Act: -0.0005

Data Index: 1111352 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0406. Min Act: -0.0005

Data Index: 261529 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0378. Min Act: -0.0005

Data Index: 15012 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0372. Min Act: -0.0005

Data Index: 690374 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0397. Min Act: -0.0005

Data Index: 91984 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0400. Min Act: -0.0005

Data Index: 527075 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0413. Min Act: -0.0005

Data Index: 870133 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0411. Min Act: -0.0005

Data Index: 388295 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0363. Min Act: -0.0005

Data Index: 139049 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0389. Min Act: -0.0005

Data Index: 501381 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0371. Min Act: -0.0005

Data Index: 1201598 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1319279 (C4 (Web Text))

Max Activating Token Index: 441