Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2482 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4354. Min Act: -0.0000

Data Index: 550336 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1835111 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3552. Min Act: -0.0000

Data Index: 24854 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1529504 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1133845 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1744205 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3261. Min Act: -0.0000

Data Index: 372521 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1738755 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3029. Min Act: -0.0000

Data Index: 895745 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2954. Min Act: -0.0000

Data Index: 515091 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2899. Min Act: -0.0000

Data Index: 357159 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2676. Min Act: -0.0000

Data Index: 413048 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1802047 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3057. Min Act: -0.0000

Data Index: 972570 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1912507 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1180104 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2760. Min Act: -0.0000

Data Index: 492004 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2735. Min Act: -0.0000

Data Index: 185311 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2914. Min Act: -0.0000

Data Index: 63346 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1022693 (The Pile)

Max Activating Token Index: 735