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

Dataset: The Pile

Neuron 502 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: 0.5661. Min Range: -0.5661

Max Act: 0.5661. Min Act: -0.0000

Data Index: 595516 (The Pile)

Max Activating Token Index: 569

Text #1

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5278. Min Act: -0.0000

Data Index: 976014 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5248. Min Act: -0.0000

Data Index: 126989 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1784597 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1319784 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1697670 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4991. Min Act: -0.0000

Data Index: 562124 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1718743 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4990. Min Act: -0.0000

Data Index: 999416 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1009560 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1448790 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1552188 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1147180 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4453. Min Act: -0.0000

Data Index: 16229 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4946. Min Act: -0.0000

Data Index: 535218 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4670. Min Act: -0.0000

Data Index: 801357 (The Pile)

Max Activating Token Index: 488

Text #16

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1387069 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1362268 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4758. Min Act: -0.0000

Data Index: 577782 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1176769 (The Pile)

Max Activating Token Index: 695