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

Dataset: The Pile

Neuron 4696 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.6511. Min Act: -0.0000

Data Index: 176206 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.0419. Min Act: -0.0000

Data Index: 752351 (The Pile)

Max Activating Token Index: 255

Text #2

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.4697. Min Act: -0.0000

Data Index: 1617488 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.9933. Min Act: -0.0000

Data Index: 1561703 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 3.6511. Min Range: -3.6511

Max Act: 3.0790. Min Act: -0.0000

Data Index: 689712 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.8332. Min Act: -0.0000

Data Index: 1485964 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.7091. Min Act: -0.0000

Data Index: 1004407 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.8287. Min Act: -0.0000

Data Index: 1454959 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.7825. Min Act: 0.0000

Data Index: 669960 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.5780. Min Act: -0.0000

Data Index: 947112 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.7433. Min Act: -0.0000

Data Index: 1827582 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.4733. Min Act: -0.0000

Data Index: 730520 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.1639. Min Act: -0.0000

Data Index: 1871644 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.3876. Min Act: -0.0000

Data Index: 1244121 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.1700. Min Act: -0.0000

Data Index: 1949927 (The Pile)

Max Activating Token Index: 771

Text #15

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.3626. Min Act: -0.0000

Data Index: 1530400 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.3470. Min Act: -0.0000

Data Index: 835508 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1754431 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.3153. Min Act: -0.0000

Data Index: 206614 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 3.6511. Min Range: -3.6511

Max Act: 2.1741. Min Act: -0.0000

Data Index: 1505583 (The Pile)

Max Activating Token Index: 361