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

Dataset: The Pile

Neuron 2583 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: 0.9297. Min Range: -0.9297

Max Act: 0.9297. Min Act: -0.0000

Data Index: 810006 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8911. Min Act: -0.0000

Data Index: 85867 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1596157 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6942. Min Act: -0.0000

Data Index: 323271 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1397269 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1203960 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6691. Min Act: -0.0000

Data Index: 449254 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6428. Min Act: -0.0000

Data Index: 468548 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6750. Min Act: -0.0000

Data Index: 768972 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1731918 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6448. Min Act: -0.0000

Data Index: 583639 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6101. Min Act: -0.0000

Data Index: 455218 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1380017 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6139. Min Act: -0.0000

Data Index: 927267 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6119. Min Act: -0.0000

Data Index: 864199 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1159262 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1996699 (The Pile)

Max Activating Token Index: 992

Text #17

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1570311 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6099. Min Act: -0.0000

Data Index: 119510 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6283. Min Act: -0.0000

Data Index: 470473 (The Pile)

Max Activating Token Index: 12