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

Dataset: The Pile

Neuron 1575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.3921. Min Act: -0.0000

Data Index: 1268770 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.2444. Min Act: -0.0000

Data Index: 799476 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.1948. Min Act: -0.0001

Data Index: 143135 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0894. Min Act: -0.0000

Data Index: 1835569 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0990. Min Act: -0.0000

Data Index: 1601349 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.9411. Min Act: -0.0000

Data Index: 644606 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.9212. Min Act: -0.0000

Data Index: 10578 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.7670. Min Act: -0.0001

Data Index: 30707 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0370. Min Act: -0.0000

Data Index: 385399 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0249. Min Act: -0.0000

Data Index: 1253561 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.1416. Min Act: -0.0000

Data Index: 1137995 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0223. Min Act: -0.0000

Data Index: 83311 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.8877. Min Act: -0.0000

Data Index: 1404503 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.8440. Min Act: -0.0000

Data Index: 1458863 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.9557. Min Act: -0.0000

Data Index: 188374 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0859. Min Act: -0.0000

Data Index: 294754 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.8108. Min Act: -0.0000

Data Index: 1829453 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0769. Min Act: -0.0000

Data Index: 1957058 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 3.3921. Min Range: -3.3921

Max Act: 2.9875. Min Act: -0.0000

Data Index: 270583 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 3.3921. Min Range: -3.3921

Max Act: 3.0493. Min Act: -0.0000

Data Index: 1033195 (The Pile)

Max Activating Token Index: 731