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

Dataset: The Pile

Neuron 975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.7006. Min Act: -0.0000

Data Index: 1247802 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1777462 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1090651 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 1.7006. Min Range: -1.7006

Max Act: 0.8771. Min Act: -0.0000

Data Index: 259844 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2992. Min Act: -0.0000

Data Index: 139198 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2140. Min Act: -0.0000

Data Index: 815144 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.2066. Min Act: -0.0000

Data Index: 453210 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1188790 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0458. Min Act: -0.0000

Data Index: 669068 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1738723 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 1.7006. Min Range: -1.7006

Max Act: 0.9777. Min Act: -0.0000

Data Index: 427088 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1827249 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1204549 (The Pile)

Max Activating Token Index: 523

Text #13

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1158774 (The Pile)

Max Activating Token Index: 450

Text #14

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1992272 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1011217 (The Pile)

Max Activating Token Index: 963

Text #16

Max Range: 1.7006. Min Range: -1.7006

Max Act: 0.9709. Min Act: -0.0000

Data Index: 784524 (The Pile)

Max Activating Token Index: 882

Text #17

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1584391 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 1.7006. Min Range: -1.7006

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1980775 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.7006. Min Range: -1.7006

Max Act: 0.9841. Min Act: -0.0000

Data Index: 435689 (The Pile)

Max Activating Token Index: 758