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

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

Neuron 4964 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1352171 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.1256. Min Act: -0.0000

Data Index: 985332 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1141511 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0537. Min Act: -0.0000

Data Index: 320724 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1157245 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1291383 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0499. Min Act: -0.0000

Data Index: 502848 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0299. Min Act: -0.0000

Data Index: 58892 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0536. Min Act: -0.0000

Data Index: 351189 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1225422 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1290141 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0250. Min Act: -0.0000

Data Index: 600387 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9923. Min Act: -0.0000

Data Index: 257407 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1252199 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1349327 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1134830 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9852. Min Act: -0.0000

Data Index: 843445 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9802. Min Act: -0.0000

Data Index: 6213 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9998. Min Act: -0.0000

Data Index: 198005 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1147352 (C4 (Web Text))

Max Activating Token Index: 7