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

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

Neuron 626 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0001

Data Index: 150404 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1309349 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0366. Min Act: -0.0001

Data Index: 460936 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1148682 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0343. Min Act: -0.0001

Data Index: 864986 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0336. Min Act: -0.0001

Data Index: 327696 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0305. Min Act: -0.0001

Data Index: 680316 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0302. Min Act: -0.0001

Data Index: 476235 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0302. Min Act: -0.0001

Data Index: 338464 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0313. Min Act: -0.0001

Data Index: 642908 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0327. Min Act: -0.0001

Data Index: 878608 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1344529 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0304. Min Act: -0.0001

Data Index: 631568 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0308. Min Act: -0.0001

Data Index: 740461 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0317. Min Act: -0.0001

Data Index: 158642 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0307. Min Act: -0.0001

Data Index: 831962 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0317. Min Act: -0.0001

Data Index: 316229 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0295. Min Act: -0.0001

Data Index: 535688 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0320. Min Act: -0.0001

Data Index: 46185 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0298. Min Act: -0.0001

Data Index: 477695 (C4 (Web Text))

Max Activating Token Index: 39