Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2107 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0003

Data Index: 112063 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0990. Min Act: -0.0003

Data Index: 665077 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0905. Min Act: -0.0003

Data Index: 1310550 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0893. Min Act: -0.0003

Data Index: 885603 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1726671 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0847. Min Act: -0.0003

Data Index: 1013810 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0898. Min Act: -0.0003

Data Index: 504156 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1364997 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0826. Min Act: -0.0003

Data Index: 1490235 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0850. Min Act: -0.0003

Data Index: 197499 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0844. Min Act: -0.0003

Data Index: 1570352 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0877. Min Act: -0.0003

Data Index: 698032 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0836. Min Act: -0.0003

Data Index: 967001 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0858. Min Act: -0.0003

Data Index: 578163 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0829. Min Act: -0.0003

Data Index: 981541 (The Pile)

Max Activating Token Index: 553

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1571834 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1611524 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0822. Min Act: -0.0003

Data Index: 418336 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1236154 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1086997 (The Pile)

Max Activating Token Index: 464