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

Dataset: The Pile

Neuron 603 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: 0.7801. Min Range: -0.7801

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1271400 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.7117. Min Act: -0.0000

Data Index: 999439 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1605977 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6044. Min Act: -0.0000

Data Index: 798172 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6346. Min Act: -0.0000

Data Index: 190830 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5666. Min Act: -0.0000

Data Index: 852494 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1643956 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1935703 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1100664 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1069042 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1613624 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5630. Min Act: -0.0000

Data Index: 382536 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4868. Min Act: -0.0000

Data Index: 962811 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4696. Min Act: -0.0000

Data Index: 43570 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5127. Min Act: -0.0000

Data Index: 18119 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4772. Min Act: -0.0000

Data Index: 544818 (The Pile)

Max Activating Token Index: 216

Text #16

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4912. Min Act: -0.0000

Data Index: 704052 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1472084 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1830922 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5419. Min Act: -0.0000

Data Index: 394663 (The Pile)

Max Activating Token Index: 900