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

Dataset: The Pile

Neuron 2105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6499. Min Range: -6.6499

Max Act: 6.6499. Min Act: -0.0000

Data Index: 1368739 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 6.6499. Min Range: -6.6499

Max Act: 6.3417. Min Act: -0.0000

Data Index: 273997 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 6.6499. Min Range: -6.6499

Max Act: 6.1000. Min Act: -0.0000

Data Index: 1034017 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 6.6499. Min Range: -6.6499

Max Act: 6.0593. Min Act: -0.0000

Data Index: 610248 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.7663. Min Act: -0.0000

Data Index: 362073 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.8052. Min Act: -0.0000

Data Index: 1764209 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.8566. Min Act: -0.0000

Data Index: 1062194 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.8534. Min Act: -0.0000

Data Index: 1620033 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.6292. Min Act: -0.0000

Data Index: 901575 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 6.6499. Min Range: -6.6499

Max Act: 6.1682. Min Act: -0.0000

Data Index: 1507791 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.6987. Min Act: -0.0000

Data Index: 1786769 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.5141. Min Act: -0.0000

Data Index: 353899 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 6.6499. Min Range: -6.6499

Max Act: 4.6758. Min Act: -0.0000

Data Index: 1653406 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.6953. Min Act: -0.0000

Data Index: 441395 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.9145. Min Act: -0.0000

Data Index: 1438412 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.6727. Min Act: -0.0000

Data Index: 1907831 (The Pile)

Max Activating Token Index: 325

Text #16

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.4406. Min Act: -0.0000

Data Index: 115602 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.7925. Min Act: -0.0000

Data Index: 1308229 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.3940. Min Act: -0.0000

Data Index: 1496086 (The Pile)

Max Activating Token Index: 988

Text #19

Max Range: 6.6499. Min Range: -6.6499

Max Act: 5.6027. Min Act: -0.0000

Data Index: 1590157 (The Pile)

Max Activating Token Index: 930