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

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

Neuron 2168 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: 2.5664. Min Range: -2.5664

Max Act: 2.5664. Min Act: -0.0000

Data Index: 1231624 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.3028. Min Act: -0.0000

Data Index: 870714 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 2.5664. Min Range: -2.5664

Max Act: 1.9585. Min Act: -0.0000

Data Index: 780842 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.1824. Min Act: -0.0000

Data Index: 563068 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.2731. Min Act: -0.0000

Data Index: 1273274 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.1428. Min Act: -0.0000

Data Index: 369559 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.1370. Min Act: -0.0000

Data Index: 436041 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.1333. Min Act: -0.0000

Data Index: 1279928 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 2.5664. Min Range: -2.5664

Max Act: 1.9927. Min Act: -0.0000

Data Index: 460186 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.0933. Min Act: -0.0000

Data Index: 1179522 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.2969. Min Act: -0.0000

Data Index: 209904 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.0059. Min Act: -0.0000

Data Index: 1302659 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.0677. Min Act: -0.0000

Data Index: 80763 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.0573. Min Act: -0.0000

Data Index: 716096 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 2.5664. Min Range: -2.5664

Max Act: 1.9322. Min Act: -0.0000

Data Index: 416667 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.1465. Min Act: -0.0000

Data Index: 208031 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.0332. Min Act: -0.0000

Data Index: 1270000 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 2.5664. Min Range: -2.5664

Max Act: 1.9806. Min Act: -0.0000

Data Index: 79008 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 2.5664. Min Range: -2.5664

Max Act: 1.9250. Min Act: -0.0000

Data Index: 1161954 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 2.5664. Min Range: -2.5664

Max Act: 2.1250. Min Act: -0.0000

Data Index: 28503 (C4 (Web Text))

Max Activating Token Index: 65