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

Dataset: The Pile

Neuron 3498 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: 0.8673. Min Range: -0.8673

Max Act: 0.8673. Min Act: -0.0000

Data Index: 41054 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.8142. Min Act: -0.0000

Data Index: 640232 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1967479 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1398061 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6443. Min Act: -0.0000

Data Index: 289150 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1293639 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6837. Min Act: -0.0000

Data Index: 584305 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6655. Min Act: -0.0000

Data Index: 833805 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6107. Min Act: -0.0000

Data Index: 550710 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1963561 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6250. Min Act: -0.0000

Data Index: 690454 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.5789. Min Act: -0.0000

Data Index: 816016 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6009. Min Act: -0.0000

Data Index: 610865 (The Pile)

Max Activating Token Index: 52

Text #13

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.6405. Min Act: -0.0000

Data Index: 561648 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.5864. Min Act: -0.0000

Data Index: 786677 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.5592. Min Act: -0.0000

Data Index: 218967 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.5374. Min Act: -0.0000

Data Index: 511211 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.5180. Min Act: -0.0000

Data Index: 416734 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1801915 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 0.8673. Min Range: -0.8673

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1673038 (The Pile)

Max Activating Token Index: 403