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

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

Neuron 2221 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: 0.7357. Min Range: -0.7357

Max Act: 0.7357. Min Act: 0.0001

Data Index: 1539539 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6356. Min Act: 0.0001

Data Index: 1492972 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5348. Min Act: 0.0001

Data Index: 1583797 (Python Code)

Max Activating Token Index: 544

Text #3

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5784. Min Act: 0.0001

Data Index: 1438277 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5559. Min Act: 0.0000

Data Index: 1471453 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5561. Min Act: 0.0001

Data Index: 1480176 (Python Code)

Max Activating Token Index: 352

Text #6

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5596. Min Act: 0.0001

Data Index: 1591747 (Python Code)

Max Activating Token Index: 972

Text #7

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5259. Min Act: 0.0001

Data Index: 1520858 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1399821 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1654318 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5149. Min Act: 0.0001

Data Index: 1474168 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1365366 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1647362 (Python Code)

Max Activating Token Index: 628

Text #13

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5197. Min Act: 0.0001

Data Index: 1422529 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1474182 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1521193 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5119. Min Act: 0.0001

Data Index: 1574289 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1465369 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1459942 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4725. Min Act: 0.0001

Data Index: 1557622 (Python Code)

Max Activating Token Index: 8