Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2948 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8227. Min Act: -0.0000

Data Index: 100083 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1565337 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7739. Min Act: -0.0000

Data Index: 453781 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7547. Min Act: -0.0000

Data Index: 125997 (The Pile)

Max Activating Token Index: 705

Text #4

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6990. Min Act: -0.0000

Data Index: 204452 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1825994 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7140. Min Act: -0.0000

Data Index: 824771 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7439. Min Act: -0.0000

Data Index: 665102 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7009. Min Act: -0.0000

Data Index: 891088 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1136982 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1670908 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6663. Min Act: -0.0000

Data Index: 187799 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6784. Min Act: -0.0000

Data Index: 58906 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1896876 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6986. Min Act: -0.0000

Data Index: 780995 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1241698 (The Pile)

Max Activating Token Index: 703

Text #16

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1112062 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6566. Min Act: -0.0000

Data Index: 709827 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1698562 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1056369 (The Pile)

Max Activating Token Index: 170