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

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

Neuron 3802 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: 2.0326. Min Range: -2.0326

Max Act: 2.0174. Min Act: -0.0000

Data Index: 679596 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 2.0326. Min Range: -2.0326

Max Act: 2.0326. Min Act: -0.0000

Data Index: 1594159 (Python Code)

Max Activating Token Index: 239

Text #2

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1617860 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.5780. Min Act: -0.0000

Data Index: 1599902 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.4421. Min Act: -0.0000

Data Index: 1491749 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1438373 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1361170 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1586718 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.2233. Min Act: -0.0000

Data Index: 1551567 (Python Code)

Max Activating Token Index: 324

Text #9

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3504. Min Act: -0.0000

Data Index: 1498406 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1453480 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1398689 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1443294 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1371974 (Python Code)

Max Activating Token Index: 928

Text #14

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1629308 (Python Code)

Max Activating Token Index: 259

Text #15

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1508427 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1599666 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1636732 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1465392 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 2.0326. Min Range: -2.0326

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1420778 (Python Code)

Max Activating Token Index: 558