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

Dataset: The Pile

Neuron 4690 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1202365 (The Pile)

Max Activating Token Index: 80

Text #1

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9273. Min Act: -0.0000

Data Index: 768937 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1258585 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1690156 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8697. Min Act: -0.0000

Data Index: 391304 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1614551 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7789. Min Act: -0.0000

Data Index: 942637 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1216304 (The Pile)

Max Activating Token Index: 800

Text #8

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1063570 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1822243 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1138940 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7852. Min Act: -0.0000

Data Index: 339355 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8130. Min Act: -0.0000

Data Index: 323338 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7662. Min Act: -0.0000

Data Index: 447890 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1962912 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7808. Min Act: -0.0000

Data Index: 914033 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7570. Min Act: -0.0000

Data Index: 632385 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7567. Min Act: -0.0000

Data Index: 814354 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7473. Min Act: -0.0000

Data Index: 670853 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1360995 (The Pile)

Max Activating Token Index: 511