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

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

Neuron 4150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1637. Min Act: -0.0002

Data Index: 645141 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1589. Min Act: -0.0002

Data Index: 1111082 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1580. Min Act: -0.0002

Data Index: 991700 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1549. Min Act: -0.0002

Data Index: 815246 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1520. Min Act: -0.0002

Data Index: 352336 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1413. Min Act: -0.0002

Data Index: 266527 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1400. Min Act: -0.0002

Data Index: 410059 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1385. Min Act: -0.0002

Data Index: 859630 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1387. Min Act: -0.0002

Data Index: 684945 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1296. Min Act: -0.0002

Data Index: 625943 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1013689 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1382. Min Act: -0.0002

Data Index: 496135 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1323. Min Act: -0.0002

Data Index: 299752 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1288. Min Act: -0.0002

Data Index: 212444 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1262. Min Act: -0.0002

Data Index: 982943 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1255. Min Act: -0.0002

Data Index: 230673 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1247. Min Act: -0.0002

Data Index: 761713 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1292. Min Act: -0.0002

Data Index: 1041657 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1182421 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1188. Min Act: -0.0002

Data Index: 1313342 (C4 (Web Text))

Max Activating Token Index: 221