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

Dataset: The Pile

Neuron 4666 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: 1.1676. Min Range: -1.1676

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1899444 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1892997 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1427223 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0325. Min Act: -0.0000

Data Index: 137016 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1109978 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1978862 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1567836 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1172899 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1158435 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1577091 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8539. Min Act: -0.0000

Data Index: 810715 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8953. Min Act: -0.0000

Data Index: 462621 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7648. Min Act: -0.0000

Data Index: 647960 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1196 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7608. Min Act: -0.0000

Data Index: 119383 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7392. Min Act: -0.0000

Data Index: 820349 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.6858. Min Act: -0.0000

Data Index: 621534 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1768461 (The Pile)

Max Activating Token Index: 902

Text #18

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7114. Min Act: -0.0000

Data Index: 350856 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.6623. Min Act: -0.0000

Data Index: 884547 (The Pile)

Max Activating Token Index: 14