Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 930 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.2185. Min Act: -0.0000

Data Index: 1488769 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1240988 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1197231 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1027. Min Act: -0.0000

Data Index: 319343 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1589. Min Act: -0.0000

Data Index: 92067 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1937350 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1286983 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0708. Min Act: -0.0000

Data Index: 332086 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1012067 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1914637 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0452. Min Act: -0.0000

Data Index: 68822 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1508846 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1858398 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0229. Min Act: -0.0000

Data Index: 214621 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0086. Min Act: 0.0000

Data Index: 788923 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1369111 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1347409 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0556. Min Act: -0.0000

Data Index: 77350 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1796302 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1021283 (The Pile)

Max Activating Token Index: 470