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

Dataset: The Pile

Neuron 527 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: 1.3744. Min Range: -1.3744

Max Act: 1.2704. Min Act: -0.0000

Data Index: 194543 (The Pile)

Max Activating Token Index: 106

Text #1

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.3744. Min Act: -0.0000

Data Index: 387124 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.1536. Min Act: -0.0000

Data Index: 596681 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1015624 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.1894. Min Act: -0.0000

Data Index: 276669 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1131933 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1531414 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1377072 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1527888 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 1.3744. Min Range: -1.3744

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1627161 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1535697 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.9696. Min Act: -0.0000

Data Index: 353622 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.9943. Min Act: -0.0000

Data Index: 635835 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1154242 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1812152 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.8994. Min Act: -0.0000

Data Index: 625645 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.9659. Min Act: -0.0000

Data Index: 930450 (The Pile)

Max Activating Token Index: 250

Text #17

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.7585. Min Act: -0.0000

Data Index: 278354 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1089203 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 1.3744. Min Range: -1.3744

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1136819 (The Pile)

Max Activating Token Index: 793