Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4487 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1236847 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1385386 (Python Code)

Max Activating Token Index: 251

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1372668 (Python Code)

Max Activating Token Index: 568

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1380076 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1513587 (Python Code)

Max Activating Token Index: 347

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1631948 (Python Code)

Max Activating Token Index: 653

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1569314 (Python Code)

Max Activating Token Index: 961

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1627730 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1368259 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1631286 (Python Code)

Max Activating Token Index: 65

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1576238 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1465435 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1625343 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1507437 (Python Code)

Max Activating Token Index: 138

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1370194 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1439334 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1526394 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1378507 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1651730 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1637964 (Python Code)

Max Activating Token Index: 357