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

Dataset: The Pile

Neuron 4594 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7741. Min Act: -0.0000

Data Index: 32383 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1805579 (The Pile)

Max Activating Token Index: 134

Text #2

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1628995 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6052. Min Act: -0.0000

Data Index: 209046 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6443. Min Act: -0.0000

Data Index: 879496 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6519. Min Act: -0.0000

Data Index: 536947 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1523035 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1438689 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1323648 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1044328 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1435987 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5788. Min Act: -0.0000

Data Index: 740944 (The Pile)

Max Activating Token Index: 344

Text #12

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5935. Min Act: -0.0000

Data Index: 356546 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5616. Min Act: -0.0000

Data Index: 235320 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6095. Min Act: -0.0000

Data Index: 921559 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5473. Min Act: -0.0000

Data Index: 293433 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5155. Min Act: -0.0000

Data Index: 503788 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1262176 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1548366 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.5087. Min Act: -0.0000

Data Index: 48377 (The Pile)

Max Activating Token Index: 93