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

Dataset: The Pile

Neuron 3363 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: 1.1536. Min Range: -1.1536

Max Act: 1.1536. Min Act: -0.0000

Data Index: 638890 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8630. Min Act: -0.0000

Data Index: 390591 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1474307 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8046. Min Act: -0.0000

Data Index: 494586 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8024. Min Act: -0.0000

Data Index: 451810 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1938546 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8001. Min Act: -0.0000

Data Index: 46273 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1511142 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1294581 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1114659 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1066566 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.7589. Min Act: -0.0000

Data Index: 401610 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1241999 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.7459. Min Act: -0.0000

Data Index: 855512 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1266832 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.6870. Min Act: -0.0000

Data Index: 795119 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1158873 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.7799. Min Act: -0.0000

Data Index: 557334 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1920411 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.1536. Min Range: -1.1536

Max Act: 0.6873. Min Act: -0.0000

Data Index: 449616 (The Pile)

Max Activating Token Index: 383