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

Dataset: The Pile

Neuron 4617 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: 5.0496. Min Range: -5.0496

Max Act: 5.0496. Min Act: -0.0000

Data Index: 747501 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.9007. Min Act: -0.0000

Data Index: 1815252 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.8545. Min Act: -0.0000

Data Index: 970563 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.6343. Min Act: -0.0000

Data Index: 262008 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.6477. Min Act: -0.0000

Data Index: 260107 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.6349. Min Act: -0.0000

Data Index: 1806811 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.6088. Min Act: -0.0000

Data Index: 1776222 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.1408. Min Act: -0.0000

Data Index: 1741944 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.1517. Min Act: -0.0000

Data Index: 1196135 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.1146. Min Act: -0.0000

Data Index: 139610 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.1068. Min Act: -0.0000

Data Index: 1005488 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 5.0496. Min Range: -5.0496

Max Act: 4.3974. Min Act: -0.0000

Data Index: 413584 (The Pile)

Max Activating Token Index: 898

Text #12

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.7106. Min Act: -0.0000

Data Index: 410714 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.9763. Min Act: -0.0000

Data Index: 1113365 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.9568. Min Act: -0.0000

Data Index: 1562454 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.7960. Min Act: -0.0000

Data Index: 1453790 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.4956. Min Act: -0.0000

Data Index: 33138 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.9673. Min Act: -0.0000

Data Index: 1521241 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.7657. Min Act: -0.0000

Data Index: 725440 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 5.0496. Min Range: -5.0496

Max Act: 3.7132. Min Act: -0.0000

Data Index: 921193 (The Pile)

Max Activating Token Index: 238