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

Dataset: The Pile

Neuron 2309 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.7335. Min Act: -0.0000

Data Index: 499988 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.5463. Min Act: -0.0000

Data Index: 1570647 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1838174 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1916949 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.6468. Min Act: -0.0000

Data Index: 287498 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.5368. Min Act: -0.0000

Data Index: 1670823 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.5771. Min Act: -0.0000

Data Index: 639689 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.5432. Min Act: -0.0000

Data Index: 374657 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.3007. Min Act: -0.0000

Data Index: 733101 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1290903 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.0958. Min Act: -0.0000

Data Index: 212930 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1792550 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.3190. Min Act: -0.0000

Data Index: 361585 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.3069. Min Act: -0.0000

Data Index: 378174 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1425427 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.3693. Min Act: -0.0000

Data Index: 1222224 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1721828 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.0493. Min Act: -0.0000

Data Index: 967114 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.3141. Min Act: -0.0000

Data Index: 930852 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.7335. Min Range: -1.7335

Max Act: 1.2493. Min Act: -0.0000

Data Index: 679081 (The Pile)

Max Activating Token Index: 64