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

Dataset: The Pile

Neuron 2376 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: 7.9073. Min Range: -7.9073

Max Act: 7.8722. Min Act: -0.0000

Data Index: 116653 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.6169. Min Act: -0.0000

Data Index: 1223432 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.6598. Min Act: -0.0000

Data Index: 477338 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.8176. Min Act: -0.0000

Data Index: 1479267 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.2424. Min Act: -0.0000

Data Index: 706154 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.6746. Min Act: -0.0000

Data Index: 651284 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.9073. Min Act: -0.0000

Data Index: 467463 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.6308. Min Act: -0.0000

Data Index: 1071542 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.1683. Min Act: -0.0000

Data Index: 1697111 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 7.9073. Min Range: -7.9073

Max Act: 6.9259. Min Act: -0.0000

Data Index: 898490 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.4181. Min Act: -0.0000

Data Index: 1642479 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 7.9073. Min Range: -7.9073

Max Act: 6.9941. Min Act: -0.0000

Data Index: 689555 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.3606. Min Act: -0.0000

Data Index: 1479752 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 7.9073. Min Range: -7.9073

Max Act: 6.7458. Min Act: -0.0000

Data Index: 1658044 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.4439. Min Act: -0.0000

Data Index: 380704 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 7.9073. Min Range: -7.9073

Max Act: 7.2950. Min Act: -0.0000

Data Index: 1108495 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 7.9073. Min Range: -7.9073

Max Act: 6.4777. Min Act: -0.0000

Data Index: 325982 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 7.9073. Min Range: -7.9073

Max Act: 6.5982. Min Act: -0.0000

Data Index: 351640 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 7.9073. Min Range: -7.9073

Max Act: 6.7914. Min Act: -0.0000

Data Index: 483840 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 7.9073. Min Range: -7.9073

Max Act: 6.9939. Min Act: -0.0000

Data Index: 194889 (The Pile)

Max Activating Token Index: 427