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

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

Neuron 4566 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2729. Min Act: -0.0000

Data Index: 145101 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2484. Min Act: -0.0000

Data Index: 194957 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2528. Min Act: -0.0000

Data Index: 955088 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2127. Min Act: -0.0000

Data Index: 307119 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2237. Min Act: -0.0000

Data Index: 426771 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2106. Min Act: -0.0000

Data Index: 921329 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2099. Min Act: -0.0000

Data Index: 417534 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2050. Min Act: -0.0000

Data Index: 494352 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1987. Min Act: -0.0000

Data Index: 213233 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2039. Min Act: -0.0000

Data Index: 342931 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1077443 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2032. Min Act: -0.0000

Data Index: 668129 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1254725 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1175662 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1326907 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1755. Min Act: -0.0000

Data Index: 624831 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1731. Min Act: -0.0000

Data Index: 887617 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2000. Min Act: -0.0000

Data Index: 751045 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1176151 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1003529 (C4 (Web Text))

Max Activating Token Index: 319