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

Dataset: The Pile

Neuron 1117 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: 1.2830. Min Range: -1.2830

Max Act: 1.2830. Min Act: -0.0000

Data Index: 481152 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1120576 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0788. Min Act: -0.0000

Data Index: 506998 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.1408. Min Act: -0.0000

Data Index: 650865 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0881. Min Act: -0.0000

Data Index: 29442 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1616659 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9846. Min Act: -0.0000

Data Index: 525570 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1815805 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9458. Min Act: -0.0000

Data Index: 196008 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1470269 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0324. Min Act: -0.0000

Data Index: 608350 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0295. Min Act: 0.0000

Data Index: 436000 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0222. Min Act: -0.0000

Data Index: 683974 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1488855 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.8826. Min Act: 0.0000

Data Index: 162372 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1973056 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9150. Min Act: -0.0000

Data Index: 203189 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1698567 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1552259 (The Pile)

Max Activating Token Index: 502

Text #19

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1369535 (The Pile)

Max Activating Token Index: 304