Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0001

Data Index: 348949 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1205917 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1549164 (Python Code)

Max Activating Token Index: 372

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1331062 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1526239 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1409005 (Python Code)

Max Activating Token Index: 658

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1024258 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1607675 (Python Code)

Max Activating Token Index: 768

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0272. Min Act: -0.0001

Data Index: 40225 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0264. Min Act: -0.0001

Data Index: 333901 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0283. Min Act: -0.0001

Data Index: 729085 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1296360 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1389436 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1483567 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0285. Min Act: -0.0001

Data Index: 203524 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0315. Min Act: -0.0001

Data Index: 139822 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1376099 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1351308 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0234. Min Act: -0.0001

Data Index: 657719 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0259. Min Act: -0.0001

Data Index: 289794 (C4 (Web Text))

Max Activating Token Index: 398