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

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

Neuron 1912 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: 0.0291. Min Range: -0.0291

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1127190 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0287. Min Act: -0.0005

Data Index: 921843 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0256. Min Act: -0.0005

Data Index: 839648 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0270. Min Act: -0.0005

Data Index: 810310 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1607262 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0264. Min Act: -0.0005

Data Index: 757067 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0257. Min Act: -0.0005

Data Index: 103719 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0255. Min Act: -0.0005

Data Index: 1270059 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0265. Min Act: -0.0004

Data Index: 296884 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0259. Min Act: -0.0005

Data Index: 76258 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0258. Min Act: -0.0005

Data Index: 59146 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0246. Min Act: -0.0005

Data Index: 815309 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1443590 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0253. Min Act: -0.0005

Data Index: 1533354 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1042043 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0240. Min Act: -0.0005

Data Index: 140677 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1215590 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0239. Min Act: -0.0005

Data Index: 356926 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0258. Min Act: -0.0005

Data Index: 107001 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.0291. Min Range: -0.0291

Max Act: 0.0252. Min Act: -0.0004

Data Index: 892188 (C4 (Web Text))

Max Activating Token Index: 500