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

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

Neuron 2841 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1652. Min Act: -0.0001

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2245. Min Act: -0.0000

Data Index: 936334 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1835. Min Act: -0.0000

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1749. Min Act: -0.0001

Data Index: 282556 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1484628 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1429. Min Act: -0.0001

Data Index: 200567 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1442. Min Act: -0.0000

Data Index: 954372 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1424. Min Act: -0.0000

Data Index: 928281 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1377. Min Act: -0.0000

Data Index: 565119 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1388. Min Act: -0.0000

Data Index: 580529 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1242095 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1345. Min Act: -0.0000

Data Index: 975764 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1339. Min Act: -0.0000

Data Index: 715640 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1331. Min Act: -0.0000

Data Index: 680722 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1326. Min Act: -0.0001

Data Index: 952041 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1318. Min Act: -0.0000

Data Index: 952578 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1312. Min Act: -0.0000

Data Index: 226555 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1004386 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.0741. Min Act: -0.0001

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1132995 (C4 (Web Text))

Max Activating Token Index: 543