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

Dataset: The Pile

Neuron 269 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: 1.0248. Min Range: -1.0248

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1261481 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 1.0248. Min Range: -1.0248

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1721077 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1516609 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.8683. Min Act: -0.0000

Data Index: 301400 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9801. Min Act: -0.0000

Data Index: 547947 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9429. Min Act: -0.0000

Data Index: 43837 (The Pile)

Max Activating Token Index: 192

Text #6

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1255227 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1690811 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9345. Min Act: -0.0000

Data Index: 456771 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9029. Min Act: -0.0000

Data Index: 205412 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.8608. Min Act: -0.0000

Data Index: 807996 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1991822 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9919. Min Act: -0.0000

Data Index: 841503 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1556217 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9042. Min Act: -0.0000

Data Index: 713323 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9007. Min Act: -0.0000

Data Index: 688422 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1257328 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 1.0248. Min Range: -1.0248

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1629286 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.9530. Min Act: -0.0000

Data Index: 68782 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 1.0248. Min Range: -1.0248

Max Act: 0.8671. Min Act: -0.0000

Data Index: 791284 (The Pile)

Max Activating Token Index: 130