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

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

Neuron 1147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.5017. Min Range: -11.5017

Max Act: 11.5017. Min Act: -0.0000

Data Index: 375370 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 11.5017. Min Range: -11.5017

Max Act: 8.6225. Min Act: -0.0000

Data Index: 720396 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 11.5017. Min Range: -11.5017

Max Act: 8.3640. Min Act: -0.0000

Data Index: 1246189 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 11.5017. Min Range: -11.5017

Max Act: 3.4686. Min Act: -0.0000

Data Index: 808276 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1133438 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.2246. Min Act: -0.0000

Data Index: 40823 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1136243 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.0956. Min Act: -0.0000

Data Index: 289907 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.1612. Min Act: -0.0000

Data Index: 99775 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.0291. Min Act: -0.0000

Data Index: 209561 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1077777 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1289391 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.0405. Min Act: -0.0000

Data Index: 473695 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 11.5017. Min Range: -11.5017

Max Act: 1.4270. Min Act: -0.0000

Data Index: 1120068 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 11.5017. Min Range: -11.5017

Max Act: 5.1016. Min Act: -0.0000

Data Index: 121167 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 11.5017. Min Range: -11.5017

Max Act: 0.9853. Min Act: -0.0000

Data Index: 301607 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 11.5017. Min Range: -11.5017

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1215787 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 11.5017. Min Range: -11.5017

Max Act: 0.8841. Min Act: -0.0000

Data Index: 166313 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 11.5017. Min Range: -11.5017

Max Act: 0.9147. Min Act: -0.0000

Data Index: 61246 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 11.5017. Min Range: -11.5017

Max Act: 0.9397. Min Act: -0.0000

Data Index: 934289 (C4 (Web Text))

Max Activating Token Index: 487