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

Dataset: The Pile

Neuron 2854 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.8958. Min Act: -0.0000

Data Index: 394755 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.9015. Min Act: -0.0000

Data Index: 1282655 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.7208. Min Act: -0.0000

Data Index: 1105493 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.6034. Min Act: -0.0000

Data Index: 365073 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.5783. Min Act: -0.0000

Data Index: 945264 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.7165. Min Act: -0.0000

Data Index: 781646 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.5328. Min Act: -0.0000

Data Index: 792870 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.2745. Min Act: -0.0000

Data Index: 836153 (The Pile)

Max Activating Token Index: 815

Text #8

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.3870. Min Act: -0.0000

Data Index: 1995368 (The Pile)

Max Activating Token Index: 97

Text #9

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.3995. Min Act: -0.0000

Data Index: 1624023 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.2260. Min Act: -0.0000

Data Index: 1226791 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.5208. Min Act: -0.0000

Data Index: 322337 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.3628. Min Act: -0.0000

Data Index: 685871 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.3256. Min Act: -0.0000

Data Index: 1696806 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.2442. Min Act: -0.0000

Data Index: 1490782 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.0820. Min Act: -0.0000

Data Index: 727089 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.3827. Min Act: -0.0000

Data Index: 1736933 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.2048. Min Act: -0.0000

Data Index: 1068923 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.1547. Min Act: -0.0000

Data Index: 342408 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 3.9015. Min Range: -3.9015

Max Act: 3.1476. Min Act: -0.0000

Data Index: 832464 (The Pile)

Max Activating Token Index: 560