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

Dataset: The Pile

Neuron 3497 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0588. Min Act: -0.0000

Data Index: 136815 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1817418 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.1598. Min Act: -0.0000

Data Index: 564636 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1325528 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0598. Min Act: -0.0000

Data Index: 688028 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1124037 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9639. Min Act: -0.0000

Data Index: 10785 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1523303 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9168. Min Act: -0.0000

Data Index: 341763 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9019. Min Act: -0.0000

Data Index: 1016007 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1457985 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1917761 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8705. Min Act: -0.0000

Data Index: 357336 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1313677 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8430. Min Act: -0.0000

Data Index: 605010 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8675. Min Act: -0.0000

Data Index: 717543 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9074. Min Act: -0.0000

Data Index: 201386 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8506. Min Act: -0.0000

Data Index: 577321 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8662. Min Act: -0.0000

Data Index: 15946 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1649888 (The Pile)

Max Activating Token Index: 276