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

Dataset: The Pile

Neuron 4387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1186782 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2695. Min Act: -0.0000

Data Index: 294014 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2349. Min Act: -0.0000

Data Index: 267513 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2202. Min Act: -0.0000

Data Index: 517578 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2124. Min Act: -0.0000

Data Index: 950054 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2180. Min Act: -0.0000

Data Index: 428100 (The Pile)

Max Activating Token Index: 309

Text #6

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1911. Min Act: -0.0000

Data Index: 521057 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1049419 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1936041 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1249795 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1331839 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1938. Min Act: -0.0000

Data Index: 388102 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1155305 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1840166 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1069943 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1708665 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1621. Min Act: -0.0000

Data Index: 249746 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1578. Min Act: -0.0000

Data Index: 384082 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1025399 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.1493. Min Act: -0.0000

Data Index: 217072 (The Pile)

Max Activating Token Index: 834