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

Dataset: The Pile

Neuron 1714 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: 1.3090. Min Range: -1.3090

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1017635 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1825365 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1511293 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.2595. Min Act: -0.0000

Data Index: 262287 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1354682 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.1535. Min Act: -0.0000

Data Index: 647956 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.1890. Min Act: -0.0000

Data Index: 140924 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.1987. Min Act: -0.0000

Data Index: 787937 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1656074 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1597608 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1533006 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1659635 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0738. Min Act: -0.0000

Data Index: 845595 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0078. Min Act: -0.0000

Data Index: 402209 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1026012 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1280945 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1435929 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 1.3090. Min Range: -1.3090

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1155370 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.1215. Min Act: -0.0000

Data Index: 797202 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 1.3090. Min Range: -1.3090

Max Act: 1.0820. Min Act: -0.0000

Data Index: 616341 (The Pile)

Max Activating Token Index: 167