Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4454 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.3106. Min Act: -0.0000

Data Index: 1483956 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.3466. Min Act: -0.0000

Data Index: 613808 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1875979 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1601226 (The Pile)

Max Activating Token Index: 857

Text #4

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1792260 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9879. Min Act: -0.0000

Data Index: 781237 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1022755 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 1.3466. Min Range: -1.3466

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1900574 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9551. Min Act: -0.0000

Data Index: 38750 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9770. Min Act: -0.0000

Data Index: 1928777 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8838. Min Act: -0.0000

Data Index: 668186 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1336526 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1299261 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9155. Min Act: -0.0000

Data Index: 977086 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8506. Min Act: -0.0000

Data Index: 24548 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1329389 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8318. Min Act: -0.0000

Data Index: 897589 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1217697 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1765630 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 1.3466. Min Range: -1.3466

Max Act: 0.8824. Min Act: -0.0000

Data Index: 793540 (The Pile)

Max Activating Token Index: 415