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

Dataset: The Pile

Neuron 306 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1080428 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1460402 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3795. Min Act: -0.0000

Data Index: 291528 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3755. Min Act: -0.0000

Data Index: 980266 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3313. Min Act: -0.0000

Data Index: 792581 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3287. Min Act: -0.0000

Data Index: 522033 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3261. Min Act: 0.0000

Data Index: 1614048 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2500. Min Act: -0.0000

Data Index: 57003 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3388. Min Act: -0.0000

Data Index: 780590 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1579277 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1951954 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3137. Min Act: -0.0000

Data Index: 59577 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3039. Min Act: 0.0000

Data Index: 731849 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1175849 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3130. Min Act: -0.0000

Data Index: 546623 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.2987. Min Act: -0.0000

Data Index: 951731 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3142. Min Act: 0.0000

Data Index: 1088089 (The Pile)

Max Activating Token Index: 364

Text #17

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1048660 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3730. Min Act: 0.0000

Data Index: 1533459 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.3824. Min Range: -0.3824

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1474959 (The Pile)

Max Activating Token Index: 870