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

Dataset: The Pile

Neuron 2712 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: 0.6628. Min Range: -0.6628

Max Act: 0.5772. Min Act: -0.0000

Data Index: 558810 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1922730 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1936575 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1115986 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1294959 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1506795 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1869261 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4465. Min Act: -0.0000

Data Index: 751815 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1902331 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3986. Min Act: -0.0000

Data Index: 500821 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1993547 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4152. Min Act: -0.0000

Data Index: 159975 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3903. Min Act: -0.0000

Data Index: 512815 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4086. Min Act: -0.0000

Data Index: 77327 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4315. Min Act: -0.0000

Data Index: 363315 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1873028 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1657354 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3960. Min Act: -0.0000

Data Index: 568555 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1772490 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.4090. Min Act: -0.0000

Data Index: 673001 (The Pile)

Max Activating Token Index: 666