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

Dataset: The Pile

Neuron 1812 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: 0.1581. Min Range: -0.1581

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1654755 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1177157 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1551417 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1286. Min Act: -0.0000

Data Index: 446833 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1426323 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1743079 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1007. Min Act: -0.0000

Data Index: 539961 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.1128. Min Act: -0.0000

Data Index: 517638 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1856035 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1288159 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0880. Min Act: -0.0000

Data Index: 473172 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0913. Min Act: -0.0000

Data Index: 857781 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1960820 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0946. Min Act: -0.0000

Data Index: 769074 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1777247 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0797. Min Act: -0.0000

Data Index: 587024 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1899997 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1646316 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1430593 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 0.1581. Min Range: -0.1581

Max Act: 0.0828. Min Act: -0.0000

Data Index: 493856 (The Pile)

Max Activating Token Index: 416