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

Dataset: The Pile

Neuron 1753 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.3509. Min Range: -5.3509

Max Act: 5.3509. Min Act: -0.0000

Data Index: 1133162 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 5.3509. Min Range: -5.3509

Max Act: 5.2785. Min Act: -0.0000

Data Index: 906955 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.9320. Min Act: -0.0000

Data Index: 853374 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.6762. Min Act: -0.0000

Data Index: 504667 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.7737. Min Act: -0.0000

Data Index: 981914 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.9718. Min Act: -0.0000

Data Index: 1609557 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.6292. Min Act: -0.0000

Data Index: 1848296 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.6241. Min Act: -0.0000

Data Index: 1477238 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.5985. Min Act: -0.0000

Data Index: 791679 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.5814. Min Act: -0.0000

Data Index: 1877232 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.3267. Min Act: -0.0000

Data Index: 670195 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.7032. Min Act: -0.0000

Data Index: 440544 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.4519. Min Act: -0.0000

Data Index: 1607291 (The Pile)

Max Activating Token Index: 116

Text #13

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.4172. Min Act: -0.0000

Data Index: 887275 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.3979. Min Act: -0.0000

Data Index: 304109 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.3243. Min Act: -0.0000

Data Index: 322276 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.1307. Min Act: -0.0000

Data Index: 495142 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.3010. Min Act: -0.0000

Data Index: 187228 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.4269. Min Act: -0.0000

Data Index: 1893087 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 5.3509. Min Range: -5.3509

Max Act: 4.1738. Min Act: -0.0000

Data Index: 1894965 (The Pile)

Max Activating Token Index: 795