Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1972224 (The Pile)

Max Activating Token Index: 664

Text #1

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1634730 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4954. Min Act: -0.0000

Data Index: 943515 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4364. Min Act: -0.0000

Data Index: 276291 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1625926 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1748509 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3992. Min Act: -0.0000

Data Index: 810836 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1345521 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1120147 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1968503 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3927. Min Act: 0.0000

Data Index: 1496439 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3923. Min Act: -0.0000

Data Index: 755232 (The Pile)

Max Activating Token Index: 963

Text #12

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4047. Min Act: 0.0000

Data Index: 1791303 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1287346 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3872. Min Act: -0.0000

Data Index: 545806 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3730. Min Act: -0.0000

Data Index: 531760 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3883. Min Act: -0.0000

Data Index: 457358 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3678. Min Act: -0.0000

Data Index: 302569 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3795. Min Act: -0.0000

Data Index: 297888 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1483835 (The Pile)

Max Activating Token Index: 370