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

Dataset: The Pile

Neuron 2045 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: 0.7644. Min Range: -0.7644

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1320074 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1783987 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1872421 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1767412 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6207. Min Act: -0.0000

Data Index: 555568 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1947847 (The Pile)

Max Activating Token Index: 198

Text #6

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1910854 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6076. Min Act: -0.0000

Data Index: 955248 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6312. Min Act: -0.0000

Data Index: 628833 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1149832 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1830030 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1034671 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5765. Min Act: -0.0000

Data Index: 275679 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1755091 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5607. Min Act: -0.0000

Data Index: 916757 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5773. Min Act: -0.0000

Data Index: 682131 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5798. Min Act: -0.0000

Data Index: 153959 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1928517 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5578. Min Act: -0.0000

Data Index: 681702 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5652. Min Act: -0.0000

Data Index: 356127 (The Pile)

Max Activating Token Index: 543