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

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

Neuron 2558 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.1582. Min Act: -0.0002

Data Index: 750391 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.1412. Min Act: -0.0001

Data Index: 799257 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.1275. Min Act: -0.0002

Data Index: 244639 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.1106. Min Act: -0.0003

Data Index: 716727 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0624. Min Act: -0.0003

Data Index: 1128488 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0365. Min Act: -0.0002

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0077. Min Act: -0.0002

Data Index: 1183034 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0049. Min Act: -0.0003

Data Index: 8041 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.1582. Min Range: -1.1582

Max Act: 1.0052. Min Act: -0.0003

Data Index: 352580 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9944. Min Act: -0.0002

Data Index: 1232926 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9902. Min Act: -0.0003

Data Index: 614983 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9888. Min Act: -0.0002

Data Index: 562772 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9887. Min Act: -0.0002

Data Index: 238826 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9839. Min Act: -0.0003

Data Index: 593044 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9834. Min Act: -0.0003

Data Index: 783528 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9775. Min Act: -0.0002

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9607. Min Act: -0.0003

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9545. Min Act: -0.0003

Data Index: 1252573 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9478. Min Act: -0.0002

Data Index: 359174 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 1.1582. Min Range: -1.1582

Max Act: 0.9298. Min Act: -0.0003

Data Index: 110740 (C4 (Web Text))

Max Activating Token Index: 126