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

Dataset: The Pile

Neuron 2317 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: 1.8954. Min Range: -1.8954

Max Act: 1.8954. Min Act: -0.0000

Data Index: 1682741 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.4216. Min Act: -0.0000

Data Index: 807550 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.4000. Min Act: -0.0000

Data Index: 1043572 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.2325. Min Act: -0.0000

Data Index: 280056 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.2553. Min Act: -0.0000

Data Index: 355269 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.0865. Min Act: -0.0000

Data Index: 171886 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.0752. Min Act: -0.0000

Data Index: 414658 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1124102 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.1845. Min Act: -0.0000

Data Index: 996735 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.0574. Min Act: -0.0000

Data Index: 745894 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1046086 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.0136. Min Act: -0.0000

Data Index: 193296 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.0836. Min Act: -0.0000

Data Index: 608729 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 1.8954. Min Range: -1.8954

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1062858 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 1.8954. Min Range: -1.8954

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1892782 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 1.8954. Min Range: -1.8954

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1860784 (The Pile)

Max Activating Token Index: 325

Text #16

Max Range: 1.8954. Min Range: -1.8954

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1425684 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 1.8954. Min Range: -1.8954

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1323574 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 1.8954. Min Range: -1.8954

Max Act: 0.9651. Min Act: -0.0000

Data Index: 802374 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.8954. Min Range: -1.8954

Max Act: 0.8891. Min Act: 0.0000

Data Index: 1023590 (The Pile)

Max Activating Token Index: 50