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

Dataset: The Pile

Neuron 3599 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0646. Min Act: -0.0000

Data Index: 1575966 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.2181. Min Act: -0.0000

Data Index: 398011 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.8430. Min Act: -0.0000

Data Index: 1962042 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.8980. Min Act: -0.0000

Data Index: 713164 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.6770. Min Act: -0.0000

Data Index: 1930020 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.9293. Min Act: -0.0000

Data Index: 1911082 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.6029. Min Act: 0.0001

Data Index: 630478 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.5789. Min Act: -0.0000

Data Index: 1802369 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.4661. Min Act: -0.0000

Data Index: 951112 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.2799. Min Act: -0.0000

Data Index: 113498 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.6935. Min Act: -0.0000

Data Index: 1669707 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.4618. Min Act: -0.0000

Data Index: 804807 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.1939. Min Act: -0.0000

Data Index: 1617308 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.2918. Min Act: -0.0000

Data Index: 697142 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.3635. Min Act: -0.0000

Data Index: 1315890 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.3555. Min Act: 0.0000

Data Index: 1797677 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.3613. Min Act: -0.0000

Data Index: 807178 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.3367. Min Act: -0.0000

Data Index: 528629 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.3179. Min Act: -0.0000

Data Index: 606419 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 3.2181. Min Range: -3.2181

Max Act: 2.4068. Min Act: -0.0000

Data Index: 624915 (The Pile)

Max Activating Token Index: 852