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

Dataset: The Pile

Neuron 326 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: 1.0925. Min Range: -1.0925

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1615446 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 1.0925. Min Range: -1.0925

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1240531 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 1.0925. Min Range: -1.0925

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1881507 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9188. Min Act: -0.0000

Data Index: 625267 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9594. Min Act: -0.0000

Data Index: 42945 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8416. Min Act: -0.0000

Data Index: 624275 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9464. Min Act: -0.0000

Data Index: 741164 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.7493. Min Act: -0.0000

Data Index: 982184 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1591379 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1548669 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1623750 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8801. Min Act: -0.0000

Data Index: 15915 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1165524 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.7677. Min Act: -0.0000

Data Index: 631686 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8801. Min Act: -0.0000

Data Index: 906851 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8170. Min Act: -0.0000

Data Index: 451907 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1626386 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1311331 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1483147 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1963349 (The Pile)

Max Activating Token Index: 797