Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2430 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.4242. Min Act: -0.0001

Data Index: 1422988 (Python Code)

Max Activating Token Index: 214

Text #1

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2727. Min Act: -0.0001

Data Index: 1332214 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2963. Min Act: -0.0001

Data Index: 1381526 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2308. Min Act: -0.0001

Data Index: 163277 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.3077. Min Act: -0.0001

Data Index: 726757 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2202. Min Act: -0.0001

Data Index: 1461281 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2474. Min Act: -0.0001

Data Index: 1186841 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2523. Min Act: -0.0001

Data Index: 1359370 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2211. Min Act: -0.0001

Data Index: 1608490 (Python Code)

Max Activating Token Index: 403

Text #9

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2297. Min Act: -0.0001

Data Index: 1378359 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2702. Min Act: -0.0001

Data Index: 579827 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1885. Min Act: -0.0001

Data Index: 951916 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2235. Min Act: -0.0001

Data Index: 1514371 (Python Code)

Max Activating Token Index: 422

Text #13

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1745. Min Act: -0.0001

Data Index: 219231 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2413. Min Act: -0.0001

Data Index: 1168761 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1687. Min Act: -0.0001

Data Index: 455172 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2270. Min Act: -0.0000

Data Index: 798456 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1794. Min Act: -0.0001

Data Index: 986023 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1405. Min Act: -0.0001

Data Index: 1401705 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1736. Min Act: -0.0001

Data Index: 1394621 (Python Code)

Max Activating Token Index: 40