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

Dataset: The Pile

Neuron 2524 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1909454 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9860. Min Act: -0.0000

Data Index: 571400 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.7379. Min Act: -0.0000

Data Index: 283072 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5829. Min Act: -0.0000

Data Index: 279435 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6847. Min Act: -0.0000

Data Index: 8436 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1522304 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6048. Min Act: -0.0000

Data Index: 444358 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1501984 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1015043 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5275. Min Act: -0.0000

Data Index: 667274 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5516. Min Act: -0.0000

Data Index: 607308 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1611350 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5007. Min Act: -0.0000

Data Index: 766927 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5419. Min Act: -0.0000

Data Index: 188957 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5548. Min Act: -0.0000

Data Index: 900982 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5401. Min Act: -0.0000

Data Index: 737519 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1955525 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1950681 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5218. Min Act: -0.0000

Data Index: 127482 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1516044 (The Pile)

Max Activating Token Index: 488