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

Dataset: The Pile

Neuron 2783 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: 1.1017. Min Range: -1.1017

Max Act: 0.9747. Min Act: -0.0000

Data Index: 927759 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 1.1017. Min Range: -1.1017

Max Act: 1.1017. Min Act: -0.0000

Data Index: 475142 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 1.1017. Min Range: -1.1017

Max Act: 1.0495. Min Act: -0.0000

Data Index: 336938 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.1017. Min Range: -1.1017

Max Act: 1.0380. Min Act: -0.0000

Data Index: 739956 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 1.1017. Min Range: -1.1017

Max Act: 1.0060. Min Act: -0.0000

Data Index: 278029 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1784416 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1367986 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1527376 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8629. Min Act: -0.0000

Data Index: 581367 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1163725 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1461833 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8767. Min Act: -0.0000

Data Index: 130926 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8212. Min Act: -0.0000

Data Index: 207190 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.8462. Min Act: -0.0000

Data Index: 786794 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.7300. Min Act: -0.0000

Data Index: 780034 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1396507 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.6169. Min Act: -0.0000

Data Index: 58113 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1786849 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1665922 (The Pile)

Max Activating Token Index: 221

Text #19

Max Range: 1.1017. Min Range: -1.1017

Max Act: 0.7212. Min Act: -0.0000

Data Index: 106523 (The Pile)

Max Activating Token Index: 85