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

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

Neuron 3070 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0004

Data Index: 1375564 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0310. Min Act: -0.0004

Data Index: 1383565 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1554007 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1560905 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0290. Min Act: -0.0004

Data Index: 1417924 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1563082 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0269. Min Act: -0.0004

Data Index: 1466755 (Python Code)

Max Activating Token Index: 132

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0262. Min Act: -0.0004

Data Index: 1537810 (Python Code)

Max Activating Token Index: 410

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0264. Min Act: -0.0004

Data Index: 1468706 (Python Code)

Max Activating Token Index: 899

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1523226 (Python Code)

Max Activating Token Index: 801

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1502891 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0252. Min Act: -0.0004

Data Index: 1572204 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1609030 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1472726 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0247. Min Act: -0.0004

Data Index: 1361274 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0241. Min Act: -0.0004

Data Index: 1410150 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0236. Min Act: -0.0004

Data Index: 1639069 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1432355 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1389018 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1396793 (Python Code)

Max Activating Token Index: 131