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

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

Neuron 3437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.1676. Min Act: -0.0000

Data Index: 33870 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0216. Min Act: -0.0000

Data Index: 788864 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1656730 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1623809 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9870. Min Act: -0.0000

Data Index: 309554 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1131500 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9172. Min Act: -0.0000

Data Index: 188926 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8816. Min Act: -0.0000

Data Index: 23387 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9795. Min Act: -0.0000

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1120896 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8735. Min Act: -0.0000

Data Index: 535572 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8728. Min Act: -0.0000

Data Index: 996750 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8702. Min Act: -0.0000

Data Index: 309274 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1008138 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8802. Min Act: -0.0000

Data Index: 887293 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7983. Min Act: -0.0000

Data Index: 987119 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8209. Min Act: -0.0000

Data Index: 923669 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1647153 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1602041 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1378683 (Python Code)

Max Activating Token Index: 234