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

Dataset: The Pile

Neuron 1864 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: 5.7032. Min Range: -5.7032

Max Act: 5.7032. Min Act: -0.0000

Data Index: 1847244 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 5.7032. Min Range: -5.7032

Max Act: 5.1190. Min Act: -0.0000

Data Index: 161937 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 5.7032. Min Range: -5.7032

Max Act: 5.0312. Min Act: -0.0000

Data Index: 639070 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.7552. Min Act: -0.0000

Data Index: 213557 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.8955. Min Act: -0.0000

Data Index: 1519574 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.5038. Min Act: -0.0000

Data Index: 185 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.8812. Min Act: -0.0000

Data Index: 970393 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.5010. Min Act: -0.0000

Data Index: 539767 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.6706. Min Act: -0.0000

Data Index: 582842 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.4087. Min Act: -0.0000

Data Index: 1611599 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.7639. Min Act: -0.0000

Data Index: 134268 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.3696. Min Act: -0.0000

Data Index: 1678730 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.2509. Min Act: -0.0000

Data Index: 1660696 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.1471. Min Act: -0.0000

Data Index: 79791 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.4412. Min Act: -0.0000

Data Index: 307560 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.5597. Min Act: -0.0000

Data Index: 1033649 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.0612. Min Act: -0.0000

Data Index: 1793593 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.3857. Min Act: -0.0000

Data Index: 132297 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.0484. Min Act: -0.0000

Data Index: 1624436 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 5.7032. Min Range: -5.7032

Max Act: 4.3386. Min Act: -0.0000

Data Index: 1567944 (The Pile)

Max Activating Token Index: 479