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

Dataset: The Pile

Neuron 4227 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: 1.5485. Min Range: -1.5485

Max Act: 1.5485. Min Act: -0.0000

Data Index: 581365 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.3951. Min Act: -0.0000

Data Index: 430552 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.4113. Min Act: -0.0000

Data Index: 908864 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1793267 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1731. Min Act: -0.0000

Data Index: 98807 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1212875 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.2068. Min Act: -0.0000

Data Index: 593297 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1441. Min Act: -0.0000

Data Index: 171550 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1713065 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1178098 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1607161 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 1.5485. Min Range: -1.5485

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1379492 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.0506. Min Act: -0.0000

Data Index: 474601 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1835985 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 1.5485. Min Range: -1.5485

Max Act: 0.9784. Min Act: -0.0000

Data Index: 616011 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 1.5485. Min Range: -1.5485

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1854753 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 1.5485. Min Range: -1.5485

Max Act: 0.9704. Min Act: -0.0000

Data Index: 226464 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.5485. Min Range: -1.5485

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1819626 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1349398 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 1.5485. Min Range: -1.5485

Max Act: 0.9622. Min Act: -0.0000

Data Index: 303971 (The Pile)

Max Activating Token Index: 525