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

Dataset: The Pile

Neuron 2130 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7255. Min Range: -3.7255

Max Act: 3.6976. Min Act: -0.0000

Data Index: 1254725 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 3.7255. Min Range: -3.7255

Max Act: 3.2722. Min Act: -0.0000

Data Index: 312775 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 3.7255. Min Range: -3.7255

Max Act: 3.7255. Min Act: -0.0000

Data Index: 1885306 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 3.7255. Min Range: -3.7255

Max Act: 3.5481. Min Act: -0.0000

Data Index: 725600 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.9923. Min Act: -0.0000

Data Index: 1516676 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 3.7255. Min Range: -3.7255

Max Act: 3.3607. Min Act: -0.0000

Data Index: 1267856 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 3.7255. Min Range: -3.7255

Max Act: 3.0575. Min Act: -0.0000

Data Index: 1606163 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 3.7255. Min Range: -3.7255

Max Act: 3.1762. Min Act: -0.0000

Data Index: 1291740 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.7000. Min Act: -0.0000

Data Index: 1825117 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.9180. Min Act: -0.0000

Data Index: 1585874 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.8641. Min Act: -0.0000

Data Index: 1626564 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.6942. Min Act: -0.0000

Data Index: 163537 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.8128. Min Act: -0.0000

Data Index: 78493 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.7301. Min Act: -0.0000

Data Index: 258198 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.7150. Min Act: -0.0000

Data Index: 1121675 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.4335. Min Act: -0.0000

Data Index: 580245 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.6733. Min Act: -0.0000

Data Index: 872948 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.4033. Min Act: -0.0000

Data Index: 1073711 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.6572. Min Act: -0.0000

Data Index: 953181 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 3.7255. Min Range: -3.7255

Max Act: 2.6446. Min Act: -0.0000

Data Index: 1147845 (The Pile)

Max Activating Token Index: 365