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

Dataset: The Pile

Neuron 3214 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: 0.3645. Min Range: -0.3645

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1610727 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3366. Min Act: -0.0000

Data Index: 936739 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1497868 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1225215 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3588. Min Act: 0.0001

Data Index: 1900066 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1816397 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1463952 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1614740 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1758590 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1510520 (The Pile)

Max Activating Token Index: 358

Text #10

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1680984 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3246. Min Act: -0.0000

Data Index: 703914 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1587560 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1859263 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2872. Min Act: -0.0000

Data Index: 630719 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1097363 (The Pile)

Max Activating Token Index: 873

Text #16

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1611172 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1035378 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2574. Min Act: -0.0000

Data Index: 666621 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2768. Min Act: -0.0000

Data Index: 819812 (The Pile)

Max Activating Token Index: 322