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

Dataset: The Pile

Neuron 2666 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: 1.9517. Min Range: -1.9517

Max Act: 1.9517. Min Act: -0.0000

Data Index: 1228906 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.6925. Min Act: -0.0000

Data Index: 825743 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5639. Min Act: -0.0000

Data Index: 689046 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.5040. Min Act: -0.0000

Data Index: 328448 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.4936. Min Act: -0.0000

Data Index: 103954 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.4925. Min Act: -0.0000

Data Index: 766744 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1275732 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.4272. Min Act: -0.0000

Data Index: 379064 (The Pile)

Max Activating Token Index: 202

Text #8

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1025260 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.4113. Min Act: -0.0000

Data Index: 649562 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1872789 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3939. Min Act: -0.0000

Data Index: 546682 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.4426. Min Act: -0.0000

Data Index: 385092 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3669. Min Act: -0.0000

Data Index: 443188 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3489. Min Act: -0.0000

Data Index: 898171 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1660854 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3373. Min Act: -0.0000

Data Index: 533353 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.3279. Min Act: -0.0000

Data Index: 115814 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.2782. Min Act: -0.0000

Data Index: 757095 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 1.9517. Min Range: -1.9517

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1629531 (The Pile)

Max Activating Token Index: 895