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

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

Neuron 2404 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.3058. Min Act: -0.0000

Data Index: 57422 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1180505 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2926. Min Act: -0.0000

Data Index: 123011 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2678. Min Act: -0.0000

Data Index: 921500 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2648. Min Act: -0.0000

Data Index: 337326 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2779. Min Act: -0.0000

Data Index: 758668 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1158275 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2679. Min Act: -0.0000

Data Index: 276960 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2336. Min Act: -0.0000

Data Index: 894008 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2389. Min Act: -0.0000

Data Index: 679138 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2345. Min Act: -0.0000

Data Index: 504451 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2175. Min Act: -0.0000

Data Index: 352322 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2331. Min Act: -0.0000

Data Index: 914505 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2333. Min Act: -0.0000

Data Index: 882131 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2263. Min Act: -0.0000

Data Index: 893991 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2158. Min Act: -0.0000

Data Index: 590515 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2016. Min Act: -0.0000

Data Index: 15420 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2150. Min Act: -0.0000

Data Index: 842723 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2059. Min Act: -0.0000

Data Index: 852771 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2124. Min Act: -0.0000

Data Index: 43933 (C4 (Web Text))

Max Activating Token Index: 51