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

Dataset: The Pile

Neuron 3315 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.9627. Min Act: -0.0000

Data Index: 860100 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.7164. Min Act: -0.0000

Data Index: 263905 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.5963. Min Act: -0.0000

Data Index: 894918 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.1493. Min Act: -0.0000

Data Index: 1631352 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.1015. Min Act: -0.0000

Data Index: 811175 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.0305. Min Act: -0.0000

Data Index: 961364 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.0199. Min Act: -0.0000

Data Index: 1477045 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.8497. Min Act: -0.0000

Data Index: 562287 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.8230. Min Act: -0.0000

Data Index: 38972 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.8345. Min Act: -0.0000

Data Index: 1498956 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.1011. Min Act: -0.0000

Data Index: 1144386 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.9632. Min Act: -0.0000

Data Index: 1160329 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.9212. Min Act: -0.0000

Data Index: 474392 (The Pile)

Max Activating Token Index: 292

Text #13

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.9015. Min Act: -0.0000

Data Index: 23434 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.9084. Min Act: -0.0000

Data Index: 309174 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.8933. Min Act: -0.0000

Data Index: 1824655 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.8589. Min Act: -0.0000

Data Index: 912828 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.7282. Min Act: -0.0000

Data Index: 996918 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 3.9627. Min Range: -3.9627

Max Act: 3.0010. Min Act: -0.0000

Data Index: 125018 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 3.9627. Min Range: -3.9627

Max Act: 2.7256. Min Act: -0.0000

Data Index: 980745 (The Pile)

Max Activating Token Index: 64