Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4453 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.7163. Min Act: -0.0000

Data Index: 412021 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6229. Min Act: -0.0000

Data Index: 574696 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1269537 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5608. Min Act: -0.0000

Data Index: 907664 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5205. Min Act: -0.0000

Data Index: 994702 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5375. Min Act: -0.0000

Data Index: 7982 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5152. Min Act: -0.0000

Data Index: 20370 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5279. Min Act: -0.0000

Data Index: 234750 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5641. Min Act: -0.0000

Data Index: 817161 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5270. Min Act: -0.0000

Data Index: 827754 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5208. Min Act: -0.0000

Data Index: 832204 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1351627 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5193. Min Act: -0.0000

Data Index: 838010 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5208. Min Act: -0.0000

Data Index: 201614 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1196871 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5258. Min Act: -0.0000

Data Index: 456411 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5012. Min Act: -0.0000

Data Index: 978339 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4979. Min Act: -0.0000

Data Index: 128986 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4967. Min Act: -0.0000

Data Index: 526310 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4924. Min Act: -0.0000

Data Index: 961944 (C4 (Web Text))

Max Activating Token Index: 546