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

Dataset: The Pile

Neuron 336 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1620403 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1892305 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7663. Min Act: -0.0000

Data Index: 25445 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1515254 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1966196 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7012. Min Act: -0.0000

Data Index: 981925 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7345. Min Act: -0.0000

Data Index: 729272 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6873. Min Act: -0.0000

Data Index: 784213 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1664352 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1132603 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6885. Min Act: -0.0000

Data Index: 928964 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7401. Min Act: -0.0000

Data Index: 991720 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6708. Min Act: -0.0000

Data Index: 599293 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1516065 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6624. Min Act: -0.0000

Data Index: 121358 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1967504 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6806. Min Act: -0.0000

Data Index: 545645 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1962780 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6398. Min Act: -0.0000

Data Index: 996886 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6528. Min Act: -0.0000

Data Index: 684026 (The Pile)

Max Activating Token Index: 664