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

Dataset: The Pile

Neuron 1421 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: 1.8198. Min Range: -1.8198

Max Act: 1.8198. Min Act: -0.0000

Data Index: 200950 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.5773. Min Act: -0.0000

Data Index: 348292 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4767. Min Act: -0.0000

Data Index: 103819 (The Pile)

Max Activating Token Index: 315

Text #3

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1469462 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4684. Min Act: -0.0000

Data Index: 812932 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1865821 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3287. Min Act: -0.0000

Data Index: 257046 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3142. Min Act: -0.0000

Data Index: 1916311 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1550007 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.4465. Min Act: -0.0000

Data Index: 626000 (The Pile)

Max Activating Token Index: 29

Text #10

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2709. Min Act: -0.0000

Data Index: 1649580 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3077. Min Act: -0.0000

Data Index: 1159873 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1401777 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3811. Min Act: -0.0000

Data Index: 668584 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1096045 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1809980 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1813678 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2754. Min Act: -0.0000

Data Index: 251756 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.2611. Min Act: -0.0000

Data Index: 523575 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 1.8198. Min Range: -1.8198

Max Act: 1.1230. Min Act: -0.0000

Data Index: 860274 (The Pile)

Max Activating Token Index: 919