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

Dataset: The Pile

Neuron 4348 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1575286 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1373030 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1337732 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6065. Min Act: -0.0000

Data Index: 315922 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1089721 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6127. Min Act: -0.0000

Data Index: 737963 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1477169 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1470862 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1645737 (The Pile)

Max Activating Token Index: 418

Text #9

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1994176 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1992149 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.3767. Min Act: -0.0000

Data Index: 924887 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1773429 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1069320 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4396. Min Act: -0.0000

Data Index: 576080 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1054970 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.3999. Min Act: -0.0000

Data Index: 396969 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4121. Min Act: -0.0000

Data Index: 192021 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.3542. Min Act: -0.0000

Data Index: 495906 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4135. Min Act: -0.0000

Data Index: 56980 (The Pile)

Max Activating Token Index: 362