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

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

Neuron 1610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6888. Min Act: -0.0002

Data Index: 1009201 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6564. Min Act: -0.0002

Data Index: 1348181 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5999. Min Act: -0.0002

Data Index: 609804 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6179. Min Act: -0.0002

Data Index: 339049 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5938. Min Act: -0.0002

Data Index: 417193 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6132. Min Act: -0.0002

Data Index: 970780 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5695. Min Act: -0.0002

Data Index: 475384 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6260. Min Act: -0.0002

Data Index: 971541 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6365. Min Act: -0.0002

Data Index: 987258 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6551. Min Act: -0.0002

Data Index: 776107 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6396. Min Act: -0.0002

Data Index: 181739 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6059. Min Act: -0.0002

Data Index: 430278 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5682. Min Act: -0.0002

Data Index: 567086 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5650. Min Act: -0.0002

Data Index: 1309664 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5816. Min Act: -0.0002

Data Index: 909281 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5769. Min Act: -0.0002

Data Index: 236477 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5932. Min Act: -0.0002

Data Index: 697803 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5932. Min Act: -0.0002

Data Index: 154737 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5932. Min Act: -0.0002

Data Index: 433929 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5729. Min Act: -0.0002

Data Index: 1224106 (C4 (Web Text))

Max Activating Token Index: 199