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

Dataset: The Pile

Neuron 2437 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: 1.2667. Min Range: -1.2667

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1549033 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1548260 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0188. Min Act: -0.0000

Data Index: 987004 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1080304 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0136. Min Act: -0.0000

Data Index: 8274 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1371679 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1715887 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1561788 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0049. Min Act: -0.0000

Data Index: 13450 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1346547 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.9524. Min Act: -0.0000

Data Index: 981195 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1610925 (The Pile)

Max Activating Token Index: 671

Text #12

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.9155. Min Act: -0.0000

Data Index: 558378 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0322. Min Act: -0.0000

Data Index: 926885 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.9157. Min Act: -0.0000

Data Index: 490331 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1987023 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.9140. Min Act: -0.0000

Data Index: 185858 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1278656 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.8581. Min Act: -0.0000

Data Index: 760655 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 1.2667. Min Range: -1.2667

Max Act: 0.8973. Min Act: -0.0000

Data Index: 767476 (The Pile)

Max Activating Token Index: 395