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

Dataset: The Pile

Neuron 1101 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: 1.1479. Min Range: -1.1479

Max Act: 1.1479. Min Act: -0.0000

Data Index: 185871 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 1.1479. Min Range: -1.1479

Max Act: 1.0445. Min Act: -0.0000

Data Index: 851898 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.9847. Min Act: -0.0000

Data Index: 117951 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.9959. Min Act: -0.0000

Data Index: 843818 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 1.1479. Min Range: -1.1479

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1654946 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.1479. Min Range: -1.1479

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1000905 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1422820 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8619. Min Act: -0.0000

Data Index: 575369 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1258353 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1733042 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8625. Min Act: -0.0000

Data Index: 572183 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8991. Min Act: -0.0000

Data Index: 373157 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8725. Min Act: -0.0000

Data Index: 480940 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1282560 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1504645 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8866. Min Act: -0.0000

Data Index: 399634 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8545. Min Act: -0.0000

Data Index: 175128 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1367979 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8833. Min Act: -0.0000

Data Index: 804510 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 1.1479. Min Range: -1.1479

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1983886 (The Pile)

Max Activating Token Index: 133