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

Dataset: The Pile

Neuron 2123 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.6258. Min Act: -0.0000

Data Index: 227176 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1014403 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1882638 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5437. Min Act: -0.0000

Data Index: 218910 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1555871 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1524507 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4652. Min Act: -0.0000

Data Index: 751487 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1307594 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5176. Min Act: -0.0000

Data Index: 218491 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4739. Min Act: -0.0000

Data Index: 706037 (The Pile)

Max Activating Token Index: 950

Text #10

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5598. Min Act: -0.0000

Data Index: 536202 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4928. Min Act: -0.0000

Data Index: 806827 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5108. Min Act: -0.0000

Data Index: 60681 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1387787 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1167705 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1172611 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4611. Min Act: -0.0000

Data Index: 184820 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.5109. Min Act: -0.0000

Data Index: 335487 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1459828 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.6258. Min Range: -0.6258

Max Act: 0.4414. Min Act: -0.0000

Data Index: 395370 (The Pile)

Max Activating Token Index: 190