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

Dataset: The Pile

Neuron 2856 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.1998. Min Act: -0.0000

Data Index: 548527 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1460135 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0893. Min Act: -0.0000

Data Index: 183105 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1746140 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8898. Min Act: -0.0000

Data Index: 992617 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9441. Min Act: -0.0000

Data Index: 355800 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1885749 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.1998. Min Range: -1.1998

Max Act: 1.0035. Min Act: -0.0000

Data Index: 698400 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1873406 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1589759 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1891195 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1835250 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1780106 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9706. Min Act: -0.0000

Data Index: 309238 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8548. Min Act: -0.0000

Data Index: 688382 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1400663 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1104001 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1237901 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.9311. Min Act: -0.0000

Data Index: 471153 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 1.1998. Min Range: -1.1998

Max Act: 0.8713. Min Act: -0.0000

Data Index: 416674 (The Pile)

Max Activating Token Index: 15