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

Dataset: The Pile

Neuron 3671 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1255329 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2245. Min Act: -0.0000

Data Index: 630872 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2642. Min Act: -0.0000

Data Index: 854689 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1128. Min Act: -0.0000

Data Index: 52010 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1833351 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0788. Min Act: -0.0000

Data Index: 849582 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1477514 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1039585 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1252. Min Act: -0.0000

Data Index: 937402 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0128. Min Act: -0.0000

Data Index: 808771 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1807. Min Act: -0.0000

Data Index: 301167 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1278. Min Act: -0.0000

Data Index: 598932 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0936. Min Act: -0.0000

Data Index: 367271 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1156885 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0052. Min Act: -0.0000

Data Index: 543687 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1164265 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1374076 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1883796 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.0017. Min Act: -0.0000

Data Index: 533085 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 1.5471. Min Range: -1.5471

Max Act: 0.9595. Min Act: -0.0000

Data Index: 31526 (The Pile)

Max Activating Token Index: 703