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

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

Neuron 1652 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1217054 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0393. Min Act: -0.0002

Data Index: 13871 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0382. Min Act: -0.0002

Data Index: 879116 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0378. Min Act: -0.0002

Data Index: 99277 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0388. Min Act: -0.0002

Data Index: 798145 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1307257 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1158612 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1324298 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1028699 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0351. Min Act: -0.0002

Data Index: 538150 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0339. Min Act: -0.0002

Data Index: 824380 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0328. Min Act: -0.0002

Data Index: 341349 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0317. Min Act: -0.0002

Data Index: 240637 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0309. Min Act: -0.0002

Data Index: 644047 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1268328 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1339304 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0317. Min Act: -0.0002

Data Index: 426142 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0315. Min Act: -0.0001

Data Index: 66225 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0321. Min Act: -0.0002

Data Index: 464376 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0312. Min Act: -0.0002

Data Index: 990008 (C4 (Web Text))

Max Activating Token Index: 381