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

Dataset: The Pile

Neuron 3798 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7596. Min Act: -0.0000

Data Index: 341654 (The Pile)

Max Activating Token Index: 901

Text #1

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.8688. Min Act: -0.0000

Data Index: 840524 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1996993 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6790. Min Act: -0.0000

Data Index: 772381 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.8567. Min Act: -0.0000

Data Index: 973899 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1801591 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6889. Min Act: -0.0000

Data Index: 138876 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6780. Min Act: -0.0000

Data Index: 498919 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6636. Min Act: -0.0000

Data Index: 204601 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6819. Min Act: -0.0000

Data Index: 387210 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6632. Min Act: -0.0000

Data Index: 422489 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1204287 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1771884 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6331. Min Act: -0.0000

Data Index: 659812 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6763. Min Act: -0.0000

Data Index: 683800 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1658393 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6317. Min Act: -0.0000

Data Index: 734908 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1243815 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1202627 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6191. Min Act: -0.0000

Data Index: 423649 (The Pile)

Max Activating Token Index: 314