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

Dataset: The Pile

Neuron 810 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1581802 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.2193. Min Act: -0.0000

Data Index: 970722 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.1413. Min Act: -0.0000

Data Index: 449227 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0678. Min Act: -0.0000

Data Index: 229986 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.1085. Min Act: -0.0000

Data Index: 661755 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0634. Min Act: -0.0000

Data Index: 650213 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9687. Min Act: -0.0000

Data Index: 560476 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9647. Min Act: -0.0000

Data Index: 789414 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9868. Min Act: -0.0000

Data Index: 518651 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9321. Min Act: -0.0000

Data Index: 158266 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.8757. Min Act: -0.0000

Data Index: 31378 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0006. Min Act: -0.0000

Data Index: 708503 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1561083 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9053. Min Act: -0.0000

Data Index: 643450 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1613003 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1834827 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9963. Min Act: -0.0000

Data Index: 618848 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9587. Min Act: -0.0000

Data Index: 207481 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1110329 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9268. Min Act: -0.0000

Data Index: 951446 (The Pile)

Max Activating Token Index: 886