Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4723 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2834. Min Act: -0.0001

Data Index: 712858 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2848. Min Act: -0.0001

Data Index: 899398 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2506. Min Act: -0.0000

Data Index: 42132 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1138114 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1920. Min Act: -0.0001

Data Index: 440820 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1263021 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2150. Min Act: -0.0001

Data Index: 644461 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1963. Min Act: -0.0000

Data Index: 200883 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1885. Min Act: -0.0000

Data Index: 333208 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1966. Min Act: -0.0000

Data Index: 552831 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1467441 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.2057. Min Act: -0.0000

Data Index: 961577 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1194654 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1035991 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1705. Min Act: -0.0001

Data Index: 764168 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1623. Min Act: -0.0000

Data Index: 831257 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1742. Min Act: -0.0000

Data Index: 845779 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1745. Min Act: -0.0001

Data Index: 502969 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.2848. Min Range: -0.2848

Max Act: 0.1793. Min Act: -0.0000

Data Index: 49686 (C4 (Web Text))

Max Activating Token Index: 560