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

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

Neuron 4726 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: 3.7678. Min Range: -3.7678

Max Act: 3.6283. Min Act: -0.0000

Data Index: 1507028 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.7678. Min Act: -0.0000

Data Index: 1512335 (Python Code)

Max Activating Token Index: 1001

Text #2

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.7186. Min Act: -0.0000

Data Index: 1482758 (Python Code)

Max Activating Token Index: 252

Text #3

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.5376. Min Act: -0.0000

Data Index: 1444099 (Python Code)

Max Activating Token Index: 601

Text #4

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.1990. Min Act: -0.0000

Data Index: 1645570 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.1401. Min Act: -0.0000

Data Index: 1649942 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9332. Min Act: -0.0000

Data Index: 1607940 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9380. Min Act: -0.0000

Data Index: 1553398 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.8787. Min Act: -0.0000

Data Index: 1542984 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.6277. Min Act: -0.0000

Data Index: 1537270 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.4667. Min Act: -0.0000

Data Index: 1514054 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.4268. Min Act: -0.0000

Data Index: 1423362 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.4268. Min Act: -0.0000

Data Index: 1626730 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.5215. Min Act: -0.0000

Data Index: 1462122 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.5503. Min Act: -0.0000

Data Index: 1577295 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.2830. Min Act: -0.0000

Data Index: 1550521 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.3732. Min Act: -0.0000

Data Index: 1614820 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.3512. Min Act: -0.0000

Data Index: 1528601 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.4817. Min Act: -0.0000

Data Index: 1556715 (Python Code)

Max Activating Token Index: 353

Text #19

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1574830 (Python Code)

Max Activating Token Index: 195