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

Dataset: The Pile

Neuron 107 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: 0.5033. Min Range: -0.5033

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1256799 (The Pile)

Max Activating Token Index: 938

Text #1

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1355612 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4513. Min Act: -0.0000

Data Index: 569789 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4586. Min Act: -0.0000

Data Index: 532032 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1061565 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1676172 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4253. Min Act: -0.0000

Data Index: 594566 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1644392 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3914. Min Act: -0.0000

Data Index: 509838 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1897349 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1842633 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3881. Min Act: 0.0000

Data Index: 1305358 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1987173 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1702731 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1664391 (The Pile)

Max Activating Token Index: 502

Text #15

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3521. Min Act: -0.0000

Data Index: 476530 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3577. Min Act: 0.0001

Data Index: 1721818 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3562. Min Act: 0.0000

Data Index: 922671 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1046141 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3300. Min Act: -0.0000

Data Index: 284395 (The Pile)

Max Activating Token Index: 257