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

Dataset: The Pile

Neuron 1248 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: 1.5851. Min Range: -1.5851

Max Act: 1.5223. Min Act: -0.0000

Data Index: 264978 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5851. Min Act: -0.0000

Data Index: 1453611 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1174299 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.2553. Min Act: -0.0000

Data Index: 308110 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1111804 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1564. Min Act: -0.0000

Data Index: 57800 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.2382. Min Act: -0.0000

Data Index: 852851 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1633322 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0305. Min Act: -0.0000

Data Index: 37128 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0668. Min Act: -0.0000

Data Index: 968060 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1314458 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1001905 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0352. Min Act: -0.0000

Data Index: 856578 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0342. Min Act: -0.0000

Data Index: 281470 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0935. Min Act: -0.0000

Data Index: 988108 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1887621 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1810228 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1627435 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0342. Min Act: -0.0000

Data Index: 305347 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.8951. Min Act: -0.0000

Data Index: 318036 (The Pile)

Max Activating Token Index: 20