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

Dataset: The Pile

Neuron 3166 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6557. Min Act: -0.0000

Data Index: 649026 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8056. Min Act: -0.0000

Data Index: 1165039 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8625. Min Act: -0.0000

Data Index: 119128 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7718. Min Act: -0.0000

Data Index: 1979269 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8011. Min Act: -0.0000

Data Index: 43699 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6821. Min Act: -0.0000

Data Index: 531151 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7043. Min Act: -0.0000

Data Index: 1143992 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6456. Min Act: -0.0000

Data Index: 1626465 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6540. Min Act: -0.0000

Data Index: 1522649 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6426. Min Act: -0.0000

Data Index: 351546 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1302823 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.5416. Min Act: -0.0000

Data Index: 647219 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6293. Min Act: -0.0000

Data Index: 1432828 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.5262. Min Act: -0.0000

Data Index: 1517072 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6990. Min Act: -0.0000

Data Index: 1379332 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7005. Min Act: -0.0000

Data Index: 1102205 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6039. Min Act: -0.0000

Data Index: 1366609 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3341. Min Act: -0.0000

Data Index: 1846954 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.5926. Min Act: -0.0000

Data Index: 1068926 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6452. Min Act: -0.0000

Data Index: 1703092 (The Pile)

Max Activating Token Index: 997