Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2225 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1934434 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1083881 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1552826 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.9412. Min Act: -0.0000

Data Index: 618734 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.9309. Min Act: -0.0000

Data Index: 316091 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1943475 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1011969 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1900548 (The Pile)

Max Activating Token Index: 687

Text #8

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1125659 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8283. Min Act: -0.0000

Data Index: 486067 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8579. Min Act: -0.0000

Data Index: 918605 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1726942 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1482790 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1051607 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.7807. Min Act: -0.0000

Data Index: 794479 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1053505 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1611028 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1455328 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.7865. Min Act: -0.0000

Data Index: 975412 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 1.2927. Min Range: -1.2927

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1744793 (The Pile)

Max Activating Token Index: 373