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

Dataset: The Pile

Neuron 2364 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: 5.7048. Min Range: -5.7048

Max Act: 5.7048. Min Act: -0.0000

Data Index: 708341 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 5.7048. Min Range: -5.7048

Max Act: 4.1463. Min Act: -0.0000

Data Index: 230442 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 5.7048. Min Range: -5.7048

Max Act: 3.6988. Min Act: -0.0000

Data Index: 255397 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 5.7048. Min Range: -5.7048

Max Act: 3.4678. Min Act: -0.0000

Data Index: 1184156 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 5.7048. Min Range: -5.7048

Max Act: 3.1412. Min Act: -0.0000

Data Index: 480838 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 5.7048. Min Range: -5.7048

Max Act: 3.4533. Min Act: -0.0000

Data Index: 141201 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 5.7048. Min Range: -5.7048

Max Act: 3.3252. Min Act: -0.0000

Data Index: 1917424 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 5.7048. Min Range: -5.7048

Max Act: 3.1274. Min Act: -0.0000

Data Index: 586376 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.4058. Min Act: -0.0000

Data Index: 887226 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.5221. Min Act: -0.0000

Data Index: 726546 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1801416 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.5958. Min Act: -0.0000

Data Index: 1064945 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.5025. Min Act: -0.0000

Data Index: 838265 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.0326. Min Act: -0.0000

Data Index: 1260641 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.3919. Min Act: -0.0000

Data Index: 1861672 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.1314. Min Act: -0.0000

Data Index: 1129171 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.3011. Min Act: -0.0000

Data Index: 1729876 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.1531. Min Act: -0.0000

Data Index: 1464831 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 5.7048. Min Range: -5.7048

Max Act: 2.1870. Min Act: -0.0000

Data Index: 287060 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 5.7048. Min Range: -5.7048

Max Act: 1.9567. Min Act: -0.0000

Data Index: 1639644 (The Pile)

Max Activating Token Index: 777