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

Dataset: The Pile

Neuron 537 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.4513. Min Act: -0.0000

Data Index: 756485 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3790. Min Act: -0.0000

Data Index: 1011497 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.0705. Min Act: 0.0000

Data Index: 1963476 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.1071. Min Act: -0.0000

Data Index: 660258 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.1038. Min Act: -0.0000

Data Index: 1884950 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.0550. Min Act: -0.0000

Data Index: 1960281 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.9848. Min Act: -0.0000

Data Index: 977797 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.8503. Min Act: -0.0000

Data Index: 1519887 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.9635. Min Act: -0.0000

Data Index: 1547882 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.9521. Min Act: -0.0000

Data Index: 674900 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.9247. Min Act: -0.0000

Data Index: 973942 (The Pile)

Max Activating Token Index: 598

Text #11

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.5480. Min Act: -0.0000

Data Index: 239257 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.3982. Min Act: -0.0000

Data Index: 1964763 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.8927. Min Act: -0.0000

Data Index: 232448 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.7424. Min Act: 0.0000

Data Index: 200913 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.8859. Min Act: -0.0000

Data Index: 1306361 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.8371. Min Act: -0.0000

Data Index: 1219250 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.6846. Min Act: -0.0000

Data Index: 1049725 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.8571. Min Act: -0.0000

Data Index: 991940 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 3.4513. Min Range: -3.4513

Max Act: 2.8503. Min Act: -0.0000

Data Index: 594516 (The Pile)

Max Activating Token Index: 259