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

Dataset: The Pile

Neuron 4750 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.7885. Min Act: -0.0000

Data Index: 520935 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6547. Min Act: -0.0000

Data Index: 790897 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1708413 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.6049. Min Act: -0.0000

Data Index: 388873 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1208379 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.5547. Min Act: -0.0000

Data Index: 955676 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4553. Min Act: -0.0000

Data Index: 197034 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1185926 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4428. Min Act: -0.0000

Data Index: 120162 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1567068 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1562173 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1928536 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4194. Min Act: -0.0000

Data Index: 25191 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4676. Min Act: -0.0000

Data Index: 4449 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4373. Min Act: -0.0000

Data Index: 182958 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1094276 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1604405 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1192905 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.3652. Min Act: -0.0000

Data Index: 363851 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 0.7885. Min Range: -0.7885

Max Act: 0.3828. Min Act: -0.0000

Data Index: 488365 (The Pile)

Max Activating Token Index: 123