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

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

Neuron 723 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.9516. Min Act: -0.0000

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1153932 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7644. Min Act: -0.0000

Data Index: 658644 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7597. Min Act: -0.0000

Data Index: 278036 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1505076 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6536. Min Act: -0.0000

Data Index: 537206 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1414732 (Python Code)

Max Activating Token Index: 612

Text #7

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1557228 (Python Code)

Max Activating Token Index: 750

Text #8

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6142. Min Act: -0.0000

Data Index: 809837 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6198. Min Act: -0.0000

Data Index: 363965 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1399787 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1515259 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1296684 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5800. Min Act: -0.0000

Data Index: 894862 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5536. Min Act: -0.0000

Data Index: 49818 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4588. Min Act: -0.0000

Data Index: 880539 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4851. Min Act: -0.0000

Data Index: 608155 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1422918 (Python Code)

Max Activating Token Index: 477

Text #18

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5434. Min Act: -0.0000

Data Index: 90613 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4943. Min Act: 0.0000

Data Index: 21342 (C4 (Web Text))

Max Activating Token Index: 582