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

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

Neuron 1354 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: 0.9824. Min Range: -0.9824

Max Act: 0.9824. Min Act: -0.0001

Data Index: 1626965 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1104370 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7952. Min Act: -0.0001

Data Index: 689458 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7292. Min Act: -0.0001

Data Index: 407584 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7068. Min Act: -0.0001

Data Index: 1624667 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6961. Min Act: -0.0001

Data Index: 834764 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7109. Min Act: -0.0001

Data Index: 1651897 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1370956 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6861. Min Act: -0.0001

Data Index: 1434127 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6986. Min Act: -0.0001

Data Index: 609693 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6814. Min Act: -0.0001

Data Index: 325709 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6637. Min Act: -0.0001

Data Index: 548145 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6192. Min Act: -0.0001

Data Index: 1355793 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6556. Min Act: -0.0001

Data Index: 731584 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1173853 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6230. Min Act: -0.0001

Data Index: 265660 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6217. Min Act: -0.0001

Data Index: 714686 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6297. Min Act: -0.0001

Data Index: 1459430 (Python Code)

Max Activating Token Index: 871

Text #18

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.6415. Min Act: -0.0001

Data Index: 198606 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.4912. Min Act: -0.0001

Data Index: 785183 (C4 (Web Text))

Max Activating Token Index: 849