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

Dataset: The Pile

Neuron 4814 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: 1.4183. Min Range: -1.4183

Max Act: 1.3998. Min Act: -0.0000

Data Index: 1218967 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.4183. Min Act: -0.0000

Data Index: 983840 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9968. Min Act: -0.0000

Data Index: 331643 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9670. Min Act: -0.0000

Data Index: 967711 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1855562 (The Pile)

Max Activating Token Index: 692

Text #5

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1115094 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1046081 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1430922 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1390365 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1859195 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1237727 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1458386 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1345832 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1093868 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8563. Min Act: -0.0000

Data Index: 208329 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8734. Min Act: -0.0000

Data Index: 859846 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.8355. Min Act: -0.0000

Data Index: 23377 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1950454 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.7977. Min Act: -0.0000

Data Index: 998571 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1559297 (The Pile)

Max Activating Token Index: 267