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

Dataset: The Pile

Neuron 4427 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: 5.5034. Min Range: -5.5034

Max Act: 5.5034. Min Act: -0.0000

Data Index: 227749 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 5.5034. Min Range: -5.5034

Max Act: 5.4730. Min Act: -0.0000

Data Index: 725789 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 5.5034. Min Range: -5.5034

Max Act: 5.3077. Min Act: -0.0000

Data Index: 813554 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 5.5034. Min Range: -5.5034

Max Act: 5.2357. Min Act: -0.0000

Data Index: 800247 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 5.5034. Min Range: -5.5034

Max Act: 5.1631. Min Act: -0.0000

Data Index: 1709819 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.9620. Min Act: -0.0000

Data Index: 1079613 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 5.5034. Min Range: -5.5034

Max Act: 5.2658. Min Act: -0.0000

Data Index: 1686090 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.9379. Min Act: -0.0000

Data Index: 583716 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.3714. Min Act: -0.0000

Data Index: 1745572 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.6555. Min Act: -0.0000

Data Index: 118746 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.2185. Min Act: -0.0000

Data Index: 167269 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.2984. Min Act: -0.0000

Data Index: 1821346 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.0962. Min Act: -0.0000

Data Index: 30375 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 5.5034. Min Range: -5.5034

Max Act: 4.4009. Min Act: -0.0000

Data Index: 982100 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 5.5034. Min Range: -5.5034

Max Act: 3.9353. Min Act: -0.0000

Data Index: 159885 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 5.5034. Min Range: -5.5034

Max Act: 3.2785. Min Act: -0.0000

Data Index: 1900393 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 5.5034. Min Range: -5.5034

Max Act: 3.9017. Min Act: -0.0000

Data Index: 1259080 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 5.5034. Min Range: -5.5034

Max Act: 3.9674. Min Act: -0.0000

Data Index: 315448 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 5.5034. Min Range: -5.5034

Max Act: 3.9470. Min Act: -0.0000

Data Index: 1810373 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 5.5034. Min Range: -5.5034

Max Act: 3.7392. Min Act: -0.0000

Data Index: 1651579 (The Pile)

Max Activating Token Index: 531