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

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

Neuron 4187 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6641. Min Range: -2.6641

Max Act: 2.6641. Min Act: -0.0000

Data Index: 981601 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 2.6641. Min Range: -2.6641

Max Act: 2.1730. Min Act: -0.0000

Data Index: 740096 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 2.6641. Min Range: -2.6641

Max Act: 2.0597. Min Act: -0.0000

Data Index: 279152 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.8781. Min Act: -0.0000

Data Index: 810029 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.9634. Min Act: -0.0000

Data Index: 873894 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.9112. Min Act: -0.0000

Data Index: 171267 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 2.6641. Min Range: -2.6641

Max Act: 2.0024. Min Act: -0.0000

Data Index: 235947 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.8861. Min Act: -0.0000

Data Index: 666307 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.8489. Min Act: -0.0000

Data Index: 1130546 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.7094. Min Act: -0.0000

Data Index: 927165 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1094729 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.8601. Min Act: -0.0000

Data Index: 64945 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1210916 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.6739. Min Act: -0.0000

Data Index: 216122 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.7691. Min Act: -0.0000

Data Index: 1100665 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.7418. Min Act: -0.0000

Data Index: 927172 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.6515. Min Act: -0.0000

Data Index: 165770 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.7299. Min Act: -0.0000

Data Index: 929663 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.5379. Min Act: -0.0000

Data Index: 875512 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 2.6641. Min Range: -2.6641

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1241248 (C4 (Web Text))

Max Activating Token Index: 195