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

Dataset: The Pile

Neuron 4141 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: 0.7452. Min Range: -0.7452

Max Act: 0.7452. Min Act: -0.0000

Data Index: 114952 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1422358 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6560. Min Act: -0.0000

Data Index: 469867 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.7343. Min Act: 0.0000

Data Index: 1177721 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1400991 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6368. Min Act: -0.0000

Data Index: 702369 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1345557 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1874058 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5772. Min Act: -0.0000

Data Index: 733224 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5496. Min Act: -0.0000

Data Index: 948999 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5702. Min Act: -0.0000

Data Index: 694940 (The Pile)

Max Activating Token Index: 435

Text #11

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1893763 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1808984 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5351. Min Act: -0.0000

Data Index: 521055 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5687. Min Act: 0.0000

Data Index: 849011 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1603831 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5329. Min Act: -0.0000

Data Index: 87398 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4988. Min Act: 0.0000

Data Index: 273260 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1597856 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1150688 (The Pile)

Max Activating Token Index: 984