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

Dataset: The Pile

Neuron 3947 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: 1.6106. Min Range: -1.6106

Max Act: 1.6106. Min Act: -0.0000

Data Index: 190712 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.5196. Min Act: -0.0000

Data Index: 593262 (The Pile)

Max Activating Token Index: 317

Text #2

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1867564 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.2251. Min Act: -0.0000

Data Index: 1018947 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.1676. Min Act: -0.0000

Data Index: 737937 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0893. Min Act: -0.0000

Data Index: 370158 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1716499 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.1340. Min Act: -0.0000

Data Index: 725029 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1510133 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9614. Min Act: -0.0000

Data Index: 180750 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0482. Min Act: -0.0000

Data Index: 488081 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9783. Min Act: -0.0000

Data Index: 309735 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1518606 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1330697 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0137. Min Act: 0.0000

Data Index: 137333 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1294656 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9414. Min Act: -0.0000

Data Index: 113018 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 1.6106. Min Range: -1.6106

Max Act: 1.0592. Min Act: -0.0000

Data Index: 454016 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9855. Min Act: -0.0000

Data Index: 73404 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 1.6106. Min Range: -1.6106

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1505078 (The Pile)

Max Activating Token Index: 455