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

Dataset: The Pile

Neuron 4056 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: 0.4118. Min Range: -0.4118

Max Act: 0.3835. Min Act: -0.0000

Data Index: 284119 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3519. Min Act: -0.0000

Data Index: 372401 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1633586 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3392. Min Act: -0.0000

Data Index: 94625 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1795269 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1976536 (The Pile)

Max Activating Token Index: 492

Text #6

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3257. Min Act: -0.0000

Data Index: 289477 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1444411 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1829900 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1440627 (The Pile)

Max Activating Token Index: 685

Text #10

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1593683 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1519534 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1580231 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3214. Min Act: -0.0000

Data Index: 20548 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3084. Min Act: -0.0000

Data Index: 711520 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1533686 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1894253 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2867. Min Act: -0.0000

Data Index: 171585 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1124580 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1585361 (The Pile)

Max Activating Token Index: 1013