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

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

Neuron 2016 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: 0.0352. Min Range: -0.0352

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1352924 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0301. Min Act: -0.0005

Data Index: 1369038 (Python Code)

Max Activating Token Index: 778

Text #2

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0291. Min Act: -0.0005

Data Index: 795584 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0292. Min Act: -0.0005

Data Index: 287120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0280. Min Act: -0.0005

Data Index: 12699 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0287. Min Act: -0.0005

Data Index: 1468893 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0297. Min Act: -0.0005

Data Index: 657920 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0287. Min Act: -0.0005

Data Index: 36267 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0279. Min Act: -0.0005

Data Index: 1460029 (Python Code)

Max Activating Token Index: 181

Text #9

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0265. Min Act: -0.0005

Data Index: 569843 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0258. Min Act: -0.0005

Data Index: 1499659 (Python Code)

Max Activating Token Index: 759

Text #11

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0263. Min Act: -0.0005

Data Index: 1507104 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0267. Min Act: -0.0005

Data Index: 1307051 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0272. Min Act: -0.0005

Data Index: 938888 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0271. Min Act: -0.0005

Data Index: 2780 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0259. Min Act: -0.0005

Data Index: 488626 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0268. Min Act: -0.0005

Data Index: 1395024 (Python Code)

Max Activating Token Index: 181

Text #17

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1490125 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0267. Min Act: -0.0005

Data Index: 214019 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0262. Min Act: -0.0005

Data Index: 1578736 (Python Code)

Max Activating Token Index: 274