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

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

Neuron 786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.7850. Min Act: -0.0000

Data Index: 858114 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.7718. Min Act: -0.0000

Data Index: 925902 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.8067. Min Act: -0.0000

Data Index: 550757 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.4928. Min Act: -0.0000

Data Index: 312456 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.4773. Min Act: -0.0000

Data Index: 1335849 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.4227. Min Act: -0.0000

Data Index: 509591 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.1826. Min Act: -0.0000

Data Index: 1013157 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.1986. Min Act: -0.0000

Data Index: 1132597 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.3853. Min Act: -0.0000

Data Index: 1227574 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.3588. Min Act: -0.0000

Data Index: 1339841 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.3398. Min Act: -0.0000

Data Index: 521407 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.5124. Min Act: -0.0000

Data Index: 48987 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.3503. Min Act: -0.0000

Data Index: 1359455 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.2582. Min Act: -0.0000

Data Index: 842035 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.2507. Min Act: -0.0000

Data Index: 82861 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.2440. Min Act: -0.0000

Data Index: 1308337 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.4269. Min Act: -0.0000

Data Index: 569834 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.2420. Min Act: -0.0000

Data Index: 831345 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.2236. Min Act: -0.0000

Data Index: 505434 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 4.8067. Min Range: -4.8067

Max Act: 4.2233. Min Act: -0.0000

Data Index: 536501 (C4 (Web Text))

Max Activating Token Index: 678