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

Dataset: The Pile

Neuron 964 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: 0.4786. Min Range: -0.4786

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1685831 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1416483 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3736. Min Act: -0.0000

Data Index: 319219 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3927. Min Act: -0.0000

Data Index: 524357 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3803. Min Act: -0.0000

Data Index: 811912 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3750. Min Act: -0.0000

Data Index: 572646 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3491. Min Act: -0.0000

Data Index: 448193 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1443977 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3477. Min Act: -0.0000

Data Index: 34219 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1910256 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1491120 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1115697 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3296. Min Act: -0.0000

Data Index: 124485 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3484. Min Act: -0.0000

Data Index: 574661 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1289315 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1372196 (The Pile)

Max Activating Token Index: 1015

Text #16

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1071483 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1870735 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1821184 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1959646 (The Pile)

Max Activating Token Index: 751