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

Dataset: The Pile

Neuron 3941 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: 1.2121. Min Range: -1.2121

Max Act: 1.2121. Min Act: -0.0000

Data Index: 58573 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1403564 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1579363 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1639418 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9838. Min Act: -0.0000

Data Index: 285670 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1240749 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.0323. Min Act: -0.0000

Data Index: 698227 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 1.2121. Min Range: -1.2121

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1408682 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9089. Min Act: -0.0000

Data Index: 420220 (The Pile)

Max Activating Token Index: 786

Text #9

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1051860 (The Pile)

Max Activating Token Index: 68

Text #10

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1663074 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1883076 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1375903 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8849. Min Act: -0.0000

Data Index: 554016 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7498. Min Act: -0.0000

Data Index: 76777 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8615. Min Act: -0.0000

Data Index: 512872 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1594129 (The Pile)

Max Activating Token Index: 617

Text #17

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1509882 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1714528 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 1.2121. Min Range: -1.2121

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1332117 (The Pile)

Max Activating Token Index: 7