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

Dataset: The Pile

Neuron 4020 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1051499 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.0006. Min Range: -1.0006

Max Act: 1.0006. Min Act: 0.0000

Data Index: 854086 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9681. Min Act: -0.0000

Data Index: 851962 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8828. Min Act: 0.0000

Data Index: 1671548 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9596. Min Act: -0.0000

Data Index: 75963 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9144. Min Act: -0.0000

Data Index: 597025 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8991. Min Act: -0.0000

Data Index: 390688 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1445594 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8817. Min Act: -0.0000

Data Index: 910753 (The Pile)

Max Activating Token Index: 772

Text #9

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8374. Min Act: 0.0000

Data Index: 1818388 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1038076 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1967048 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1368632 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8053. Min Act: -0.0000

Data Index: 940409 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7739. Min Act: 0.0000

Data Index: 1807521 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1997558 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7950. Min Act: 0.0000

Data Index: 1008575 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1407723 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8558. Min Act: 0.0000

Data Index: 892020 (The Pile)

Max Activating Token Index: 53

Text #19

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1859368 (The Pile)

Max Activating Token Index: 605