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

Dataset: The Pile

Neuron 3577 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: 1.0195. Min Range: -1.0195

Max Act: 1.0195. Min Act: -0.0000

Data Index: 468812 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1319492 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7999. Min Act: -0.0000

Data Index: 937502 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1305887 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8027. Min Act: -0.0000

Data Index: 388163 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7064. Min Act: -0.0000

Data Index: 61150 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7101. Min Act: -0.0000

Data Index: 178361 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1017045 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7120. Min Act: -0.0000

Data Index: 383282 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7357. Min Act: -0.0000

Data Index: 325996 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1866991 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1534740 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6741. Min Act: -0.0000

Data Index: 753011 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1721883 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6359. Min Act: -0.0000

Data Index: 717515 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1117895 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1271196 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1605718 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6009. Min Act: -0.0000

Data Index: 753219 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1245219 (The Pile)

Max Activating Token Index: 220