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

Dataset: The Pile

Neuron 1213 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: 1.4714. Min Range: -1.4714

Max Act: 1.4714. Min Act: -0.0000

Data Index: 182211 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.4041. Min Act: -0.0000

Data Index: 550715 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.2328. Min Act: -0.0000

Data Index: 227363 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.2545. Min Act: -0.0000

Data Index: 722476 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1544424 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1183479 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1596424 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1110988 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1214778 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0779. Min Act: -0.0000

Data Index: 512340 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0907. Min Act: -0.0000

Data Index: 324548 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0731. Min Act: -0.0000

Data Index: 378638 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0251. Min Act: -0.0000

Data Index: 990586 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0947. Min Act: -0.0000

Data Index: 675816 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1594158 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1422694 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.4714. Min Range: -1.4714

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1389362 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 1.4714. Min Range: -1.4714

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1408960 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 1.4714. Min Range: -1.4714

Max Act: 1.0200. Min Act: -0.0000

Data Index: 724035 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 1.4714. Min Range: -1.4714

Max Act: 0.9902. Min Act: -0.0000

Data Index: 556255 (The Pile)

Max Activating Token Index: 304