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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2601 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.5017. Min Act: -0.0000

Data Index: 588818 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.4184. Min Act: -0.0000

Data Index: 316374 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1094081 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1303470 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1106194 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3607. Min Act: -0.0000

Data Index: 291594 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3826. Min Act: -0.0000

Data Index: 838755 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3320. Min Act: -0.0000

Data Index: 944157 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3407. Min Act: -0.0000

Data Index: 566187 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3170. Min Act: -0.0000

Data Index: 65905 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1066620 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3105. Min Act: -0.0000

Data Index: 892469 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1632363 (Python Code)

Max Activating Token Index: 810

Text #13

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2940. Min Act: -0.0000

Data Index: 349641 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3102. Min Act: -0.0000

Data Index: 446061 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2904. Min Act: -0.0000

Data Index: 950727 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3198. Min Act: -0.0000

Data Index: 315191 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3228. Min Act: -0.0000

Data Index: 637154 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.3200. Min Act: -0.0000

Data Index: 878980 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.5017. Min Range: -0.5017

Max Act: 0.2925. Min Act: -0.0000

Data Index: 215678 (C4 (Web Text))

Max Activating Token Index: 856