Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1536 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1183236 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1035254 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1167288 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0421. Min Act: -0.0003

Data Index: 458328 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0370. Min Act: -0.0003

Data Index: 804545 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0396. Min Act: -0.0003

Data Index: 889309 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0363. Min Act: -0.0003

Data Index: 555821 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0397. Min Act: -0.0003

Data Index: 23642 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0385. Min Act: -0.0003

Data Index: 811066 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0387. Min Act: -0.0003

Data Index: 758794 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1061756 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0352. Min Act: -0.0003

Data Index: 849362 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0397. Min Act: -0.0003

Data Index: 788048 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0363. Min Act: -0.0003

Data Index: 999584 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0348. Min Act: -0.0003

Data Index: 670702 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0375. Min Act: -0.0003

Data Index: 957686 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0366. Min Act: -0.0003

Data Index: 899575 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0371. Min Act: -0.0003

Data Index: 772675 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1348277 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0383. Min Act: -0.0003

Data Index: 372951 (C4 (Web Text))

Max Activating Token Index: 908