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

Dataset: The Pile

Neuron 1865 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1282847 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 1.0444. Min Range: -1.0444

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1291272 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1729555 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 1.0444. Min Range: -1.0444

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1749752 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1858806 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1100802 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1502366 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7946. Min Act: -0.0000

Data Index: 796920 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7870. Min Act: -0.0000

Data Index: 881397 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1437819 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7799. Min Act: -0.0000

Data Index: 75665 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1365778 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1948330 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8630. Min Act: -0.0000

Data Index: 643862 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1474746 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7896. Min Act: -0.0000

Data Index: 844097 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7197. Min Act: -0.0000

Data Index: 207672 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6670. Min Act: -0.0000

Data Index: 286195 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1078113 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6958. Min Act: -0.0000

Data Index: 377766 (The Pile)

Max Activating Token Index: 191