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

Dataset: The Pile

Neuron 2974 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8688. Min Act: -0.0000

Data Index: 379309 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1770847 (The Pile)

Max Activating Token Index: 860

Text #2

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1117332 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1415782 (The Pile)

Max Activating Token Index: 328

Text #4

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7949. Min Act: -0.0000

Data Index: 22045 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8956. Min Act: -0.0000

Data Index: 759473 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7093. Min Act: -0.0000

Data Index: 653458 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6814. Min Act: -0.0000

Data Index: 234932 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8349. Min Act: -0.0000

Data Index: 114270 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1429729 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1128932 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7828. Min Act: -0.0000

Data Index: 745946 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1767812 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1614961 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1195368 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1458816 (The Pile)

Max Activating Token Index: 367

Text #16

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7809. Min Act: -0.0000

Data Index: 165996 (The Pile)

Max Activating Token Index: 623

Text #17

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6322. Min Act: -0.0000

Data Index: 191314 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1859380 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7014. Min Act: -0.0000

Data Index: 961813 (The Pile)

Max Activating Token Index: 915