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

Dataset: The Pile

Neuron 4118 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: 1.9752. Min Range: -1.9752

Max Act: 1.9752. Min Act: -0.0000

Data Index: 246644 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.7456. Min Act: -0.0000

Data Index: 34772 (The Pile)

Max Activating Token Index: 893

Text #2

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.7346. Min Act: -0.0000

Data Index: 406508 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.4948. Min Act: -0.0000

Data Index: 519329 (The Pile)

Max Activating Token Index: 149

Text #4

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.3300. Min Act: -0.0000

Data Index: 583250 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.3508. Min Act: -0.0000

Data Index: 450729 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.3223. Min Act: -0.0000

Data Index: 1066252 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.2386. Min Act: -0.0000

Data Index: 139408 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.1283. Min Act: -0.0000

Data Index: 29049 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1816857 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1696274 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.0965. Min Act: -0.0000

Data Index: 398014 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1844033 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.0984. Min Act: -0.0000

Data Index: 778580 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.0297. Min Act: -0.0000

Data Index: 953276 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 1.9752. Min Range: -1.9752

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1296527 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 1.9752. Min Range: -1.9752

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1508345 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 1.9752. Min Range: -1.9752

Max Act: 0.9138. Min Act: -0.0000

Data Index: 22353 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.9752. Min Range: -1.9752

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1663888 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 1.9752. Min Range: -1.9752

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1277984 (The Pile)

Max Activating Token Index: 809