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

Dataset: The Pile

Neuron 3617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1025. Min Range: -3.1025

Max Act: 3.1025. Min Act: -0.0000

Data Index: 544320 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9903. Min Act: -0.0000

Data Index: 287401 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9888. Min Act: -0.0000

Data Index: 893460 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9334. Min Act: -0.0000

Data Index: 478956 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8716. Min Act: -0.0000

Data Index: 1935591 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.7392. Min Act: -0.0000

Data Index: 243832 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.7212. Min Act: -0.0000

Data Index: 873657 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.7907. Min Act: -0.0000

Data Index: 847446 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.5125. Min Act: -0.0000

Data Index: 1213336 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.5403. Min Act: -0.0000

Data Index: 1068646 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.5085. Min Act: -0.0000

Data Index: 1714669 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.3490. Min Act: -0.0000

Data Index: 812268 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.4570. Min Act: -0.0000

Data Index: 656781 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.4574. Min Act: -0.0000

Data Index: 1935925 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1668570 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.1773. Min Act: -0.0000

Data Index: 88809 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.2527. Min Act: -0.0000

Data Index: 899544 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.4891. Min Act: -0.0000

Data Index: 1818704 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.3473. Min Act: -0.0000

Data Index: 1655270 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.2830. Min Act: -0.0000

Data Index: 172191 (The Pile)

Max Activating Token Index: 395