Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1205464 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1255. Min Act: -0.0000

Data Index: 306157 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1071179 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1062. Min Act: -0.0001

Data Index: 184884 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0984. Min Act: -0.0000

Data Index: 942940 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0948. Min Act: -0.0000

Data Index: 788121 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0907. Min Act: -0.0001

Data Index: 495632 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0844. Min Act: -0.0001

Data Index: 822735 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0739. Min Act: -0.0000

Data Index: 156684 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1164311 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1058636 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1044270 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1102376 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0634. Min Act: -0.0001

Data Index: 340542 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0673. Min Act: -0.0001

Data Index: 533318 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0710. Min Act: -0.0000

Data Index: 580148 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0619. Min Act: -0.0000

Data Index: 665257 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0688. Min Act: -0.0001

Data Index: 285262 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0677. Min Act: -0.0001

Data Index: 563237 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0629. Min Act: -0.0000

Data Index: 700801 (C4 (Web Text))

Max Activating Token Index: 114