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

Dataset: The Pile

Neuron 487 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8962. Min Act: -0.0000

Data Index: 761002 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8788. Min Act: -0.0000

Data Index: 526082 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1427931 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8681. Min Act: -0.0000

Data Index: 650238 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8696. Min Act: -0.0000

Data Index: 650096 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7760. Min Act: -0.0000

Data Index: 702993 (The Pile)

Max Activating Token Index: 724

Text #6

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8382. Min Act: -0.0000

Data Index: 765157 (The Pile)

Max Activating Token Index: 730

Text #7

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8238. Min Act: -0.0000

Data Index: 619198 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1777533 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1922235 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8058. Min Act: -0.0000

Data Index: 632786 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8185. Min Act: -0.0000

Data Index: 410438 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1257822 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1788720 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1792620 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1714388 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1684594 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1852689 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7945. Min Act: -0.0000

Data Index: 819949 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1711811 (The Pile)

Max Activating Token Index: 41