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

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

Neuron 3089 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.7161. Min Act: -0.0001

Data Index: 942133 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.5619. Min Act: -0.0001

Data Index: 664877 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.3146. Min Act: -0.0001

Data Index: 602852 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1810. Min Act: -0.0001

Data Index: 269268 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1956. Min Act: -0.0001

Data Index: 646773 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.2021. Min Act: -0.0001

Data Index: 91295 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.2720. Min Act: -0.0001

Data Index: 565765 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.2500. Min Act: -0.0001

Data Index: 520992 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1831. Min Act: -0.0001

Data Index: 566452 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1484. Min Act: -0.0001

Data Index: 1148543 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0827. Min Act: -0.0001

Data Index: 1052350 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1015. Min Act: -0.0001

Data Index: 996620 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0789. Min Act: -0.0001

Data Index: 46744 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0176. Min Act: -0.0001

Data Index: 357411 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.1297. Min Act: -0.0001

Data Index: 328298 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0667. Min Act: -0.0001

Data Index: 803614 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0814. Min Act: -0.0001

Data Index: 143916 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0560. Min Act: -0.0001

Data Index: 681901 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0512. Min Act: -0.0001

Data Index: 656406 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.7161. Min Range: -1.7161

Max Act: 1.0008. Min Act: -0.0001

Data Index: 835091 (C4 (Web Text))

Max Activating Token Index: 705