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

Dataset: The Pile

Neuron 153 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: 1.9088. Min Range: -1.9088

Max Act: 1.7401. Min Act: -0.0000

Data Index: 1830705 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.9088. Min Act: -0.0000

Data Index: 1855386 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.7034. Min Act: -0.0000

Data Index: 151111 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.7856. Min Act: -0.0000

Data Index: 37218 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5642. Min Act: -0.0000

Data Index: 1065532 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5537. Min Act: -0.0000

Data Index: 835633 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.6107. Min Act: -0.0000

Data Index: 991804 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.6037. Min Act: -0.0000

Data Index: 1612370 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1673104 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1174739 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.3394. Min Act: -0.0000

Data Index: 607619 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.6702. Min Act: -0.0000

Data Index: 732205 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.4056. Min Act: -0.0000

Data Index: 1427409 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5668. Min Act: -0.0000

Data Index: 894077 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5382. Min Act: -0.0000

Data Index: 213664 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.6421. Min Act: -0.0000

Data Index: 742536 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1771903 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.3780. Min Act: -0.0000

Data Index: 1124327 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.5264. Min Act: -0.0000

Data Index: 470570 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 1.9088. Min Range: -1.9088

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1573346 (The Pile)

Max Activating Token Index: 448