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

Dataset: The Pile

Neuron 1179 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: 0.9618. Min Range: -0.9618

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1377986 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8539. Min Act: -0.0000

Data Index: 559319 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8511. Min Act: -0.0000

Data Index: 178818 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7758. Min Act: -0.0000

Data Index: 246500 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7639. Min Act: -0.0000

Data Index: 72665 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7692. Min Act: -0.0000

Data Index: 233979 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7848. Min Act: -0.0000

Data Index: 893282 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1995344 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1877463 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7858. Min Act: -0.0000

Data Index: 637302 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7244. Min Act: -0.0000

Data Index: 322202 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7129. Min Act: -0.0000

Data Index: 318926 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1542852 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1746498 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7422. Min Act: -0.0000

Data Index: 585606 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1026118 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1292498 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7055. Min Act: -0.0000

Data Index: 435873 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1421638 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 0.9618. Min Range: -0.9618

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1696383 (The Pile)

Max Activating Token Index: 155