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

Dataset: The Pile

Neuron 3139 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1343049 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1071501 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6476. Min Act: 0.0000

Data Index: 838579 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1935638 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5447. Min Act: -0.0000

Data Index: 299433 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5591. Min Act: -0.0000

Data Index: 214007 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5225. Min Act: -0.0000

Data Index: 961523 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5379. Min Act: 0.0000

Data Index: 1261875 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5285. Min Act: -0.0000

Data Index: 998383 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.4863. Min Act: -0.0000

Data Index: 345608 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1072277 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1858416 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1256827 (The Pile)

Max Activating Token Index: 693

Text #13

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1433824 (The Pile)

Max Activating Token Index: 499

Text #14

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1899999 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5111. Min Act: -0.0000

Data Index: 392435 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1261921 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.4745. Min Act: -0.0000

Data Index: 809863 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.4751. Min Act: 0.0000

Data Index: 359286 (The Pile)

Max Activating Token Index: 918

Text #19

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1171190 (The Pile)

Max Activating Token Index: 647