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

Dataset: The Pile

Neuron 1282 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: 0.9597. Min Range: -0.9597

Max Act: 0.9597. Min Act: -0.0000

Data Index: 647684 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8892. Min Act: -0.0000

Data Index: 225385 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1833990 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1026709 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.9013. Min Act: -0.0000

Data Index: 296035 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1805608 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8790. Min Act: -0.0000

Data Index: 842224 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1943968 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.9095. Min Act: -0.0000

Data Index: 514088 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1954400 (The Pile)

Max Activating Token Index: 361

Text #10

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8462. Min Act: -0.0000

Data Index: 640713 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1970468 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8326. Min Act: -0.0000

Data Index: 402524 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1768275 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1932707 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8153. Min Act: -0.0000

Data Index: 973694 (The Pile)

Max Activating Token Index: 384

Text #16

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7516. Min Act: -0.0000

Data Index: 249991 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8710. Min Act: -0.0000

Data Index: 492238 (The Pile)

Max Activating Token Index: 545

Text #18

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7857. Min Act: -0.0000

Data Index: 543893 (The Pile)

Max Activating Token Index: 382

Text #19

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7855. Min Act: -0.0000

Data Index: 542196 (The Pile)

Max Activating Token Index: 584