Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 153 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.9827. Min Act: -0.0000

Data Index: 903287 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.9552. Min Act: -0.0000

Data Index: 176209 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.9231. Min Act: -0.0000

Data Index: 143537 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1697589 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8821. Min Act: -0.0000

Data Index: 371253 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1648310 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1579192 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1114533 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8570. Min Act: -0.0001

Data Index: 1356731 (The Pile)

Max Activating Token Index: 235

Text #9

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8829. Min Act: -0.0000

Data Index: 404524 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.9060. Min Act: -0.0000

Data Index: 319851 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1566725 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1294504 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8474. Min Act: -0.0000

Data Index: 944952 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1288201 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8238. Min Act: -0.0000

Data Index: 416202 (The Pile)

Max Activating Token Index: 791

Text #16

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8303. Min Act: -0.0000

Data Index: 990283 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1875667 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8275. Min Act: -0.0000

Data Index: 366959 (The Pile)

Max Activating Token Index: 107

Text #19

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1984276 (The Pile)

Max Activating Token Index: 908