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

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

Neuron 5277 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.1853. Min Act: -0.0002

Data Index: 1405343 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0800. Min Act: -0.0002

Data Index: 1392942 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0553. Min Act: -0.0002

Data Index: 1390549 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0514. Min Act: -0.0002

Data Index: 1508214 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0446. Min Act: -0.0002

Data Index: 355191 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0199. Min Act: -0.0002

Data Index: 1641602 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0392. Min Act: -0.0002

Data Index: 1463505 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0112. Min Act: -0.0002

Data Index: 123158 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0079. Min Act: -0.0002

Data Index: 1447730 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0267. Min Act: -0.0002

Data Index: 1479010 (Python Code)

Max Activating Token Index: 351

Text #10

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0052. Min Act: -0.0002

Data Index: 1582210 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0142. Min Act: -0.0002

Data Index: 1627476 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0047. Min Act: -0.0002

Data Index: 1457488 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9974. Min Act: -0.0002

Data Index: 1553308 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0159. Min Act: -0.0002

Data Index: 1515230 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0033. Min Act: -0.0002

Data Index: 130290 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0094. Min Act: -0.0002

Data Index: 1470637 (Python Code)

Max Activating Token Index: 136

Text #17

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9979. Min Act: -0.0002

Data Index: 1624946 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9761. Min Act: -0.0002

Data Index: 1444961 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9859. Min Act: -0.0002

Data Index: 159620 (C4 (Web Text))

Max Activating Token Index: 155