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

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

Neuron 5004 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1217. Min Act: -0.0000

Data Index: 437694 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1102. Min Act: -0.0000

Data Index: 407447 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1149. Min Act: -0.0000

Data Index: 123574 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1134343 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1094. Min Act: -0.0000

Data Index: 564047 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1026. Min Act: -0.0000

Data Index: 109828 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1042. Min Act: -0.0000

Data Index: 443095 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0977. Min Act: -0.0000

Data Index: 408363 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1009. Min Act: -0.0000

Data Index: 418565 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1000. Min Act: -0.0000

Data Index: 755169 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1303758 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.1001. Min Act: -0.0000

Data Index: 291840 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1204184 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0925. Min Act: -0.0000

Data Index: 869187 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0939. Min Act: -0.0000

Data Index: 731601 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0809. Min Act: -0.0000

Data Index: 791540 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0943. Min Act: -0.0000

Data Index: 852792 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0876. Min Act: -0.0000

Data Index: 518657 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0853. Min Act: -0.0000

Data Index: 239959 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.1217. Min Range: -0.1217

Max Act: 0.0872. Min Act: -0.0000

Data Index: 536590 (C4 (Web Text))

Max Activating Token Index: 678