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

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

Neuron 1748 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1470289 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1524195 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1507832 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1458764 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1604614 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1459089 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1429689 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1565319 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1423214 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1545773 (Python Code)

Max Activating Token Index: 414

Text #10

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1449734 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1613646 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1565762 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1601609 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1484466 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1578597 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1377117 (Python Code)

Max Activating Token Index: 539

Text #17

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1422991 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1613844 (Python Code)

Max Activating Token Index: 177

Text #19

Max Range: 0.9247. Min Range: -0.9247

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1655820 (Python Code)

Max Activating Token Index: 567