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

Dataset: The Pile

Neuron 1550 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: 0.7717. Min Range: -0.7717

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1968278 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7559. Min Act: -0.0000

Data Index: 844848 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6959. Min Act: -0.0000

Data Index: 110614 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7133. Min Act: -0.0000

Data Index: 247984 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1418258 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6476. Min Act: -0.0000

Data Index: 608875 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1334859 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1502036 (The Pile)

Max Activating Token Index: 464

Text #8

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6098. Min Act: -0.0000

Data Index: 371607 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6284. Min Act: -0.0000

Data Index: 652969 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1899959 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6650. Min Act: -0.0000

Data Index: 538390 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6402. Min Act: -0.0000

Data Index: 647218 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5728. Min Act: -0.0000

Data Index: 725911 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1577390 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5771. Min Act: -0.0000

Data Index: 106239 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1832128 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5513. Min Act: -0.0000

Data Index: 785958 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.4773. Min Act: -0.0000

Data Index: 36475 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5776. Min Act: -0.0000

Data Index: 977640 (The Pile)

Max Activating Token Index: 1022