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

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

Neuron 2759 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.6492. Min Act: -0.0000

Data Index: 124394 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1565059 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5634. Min Act: -0.0000

Data Index: 302078 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1489913 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5843. Min Act: -0.0000

Data Index: 887632 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1638402 (Python Code)

Max Activating Token Index: 116

Text #6

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1651220 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1572931 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1428443 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1524877 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1530677 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1452624 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1449873 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.4824. Min Act: -0.0000

Data Index: 357939 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1005066 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.4813. Min Act: -0.0000

Data Index: 740955 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1562242 (Python Code)

Max Activating Token Index: 491

Text #17

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1452099 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1177161 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.6492. Min Range: -0.6492

Max Act: 0.5294. Min Act: -0.0000

Data Index: 514818 (C4 (Web Text))

Max Activating Token Index: 653