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

Dataset: The Pile

Neuron 4587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1757449 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.6202. Min Act: -0.0000

Data Index: 47709 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.6067. Min Act: -0.0000

Data Index: 855802 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.6244. Min Act: -0.0000

Data Index: 386718 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5770. Min Act: -0.0000

Data Index: 870964 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5577. Min Act: -0.0000

Data Index: 75182 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1543527 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5854. Min Act: -0.0000

Data Index: 707143 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5506. Min Act: -0.0000

Data Index: 183943 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5784. Min Act: -0.0000

Data Index: 459931 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5957. Min Act: -0.0000

Data Index: 374531 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5777. Min Act: -0.0000

Data Index: 458719 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5385. Min Act: -0.0000

Data Index: 936565 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1185257 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5793. Min Act: -0.0000

Data Index: 740899 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5810. Min Act: -0.0000

Data Index: 879941 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1571371 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5634. Min Act: -0.0000

Data Index: 236380 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1686645 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5944. Min Act: -0.0000

Data Index: 383553 (The Pile)

Max Activating Token Index: 467