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

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

Neuron 1929 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.6359. Min Act: -0.0000

Data Index: 1478450 (Python Code)

Max Activating Token Index: 687

Text #1

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.8797. Min Act: -0.0000

Data Index: 1453413 (Python Code)

Max Activating Token Index: 219

Text #2

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.6179. Min Act: -0.0000

Data Index: 1605088 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.5895. Min Act: -0.0000

Data Index: 1586896 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.3957. Min Act: -0.0000

Data Index: 1492793 (Python Code)

Max Activating Token Index: 703

Text #5

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.2640. Min Act: -0.0000

Data Index: 1404572 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.1930. Min Act: -0.0000

Data Index: 1313726 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.0681. Min Act: 0.0000

Data Index: 261224 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.0726. Min Act: -0.0000

Data Index: 1594360 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.2858. Min Act: -0.0000

Data Index: 1414133 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 2.8797. Min Range: -2.8797

Max Act: 1.9463. Min Act: -0.0000

Data Index: 1367955 (Python Code)

Max Activating Token Index: 978

Text #11

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.0051. Min Act: -0.0000

Data Index: 1541057 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.1135. Min Act: -0.0000

Data Index: 1499232 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 2.8797. Min Range: -2.8797

Max Act: 2.0810. Min Act: -0.0000

Data Index: 1537254 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 2.8797. Min Range: -2.8797

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1283099 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 2.8797. Min Range: -2.8797

Max Act: 1.9835. Min Act: -0.0000

Data Index: 668 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 2.8797. Min Range: -2.8797

Max Act: 1.8091. Min Act: -0.0000

Data Index: 920143 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 2.8797. Min Range: -2.8797

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1619032 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 2.8797. Min Range: -2.8797

Max Act: 1.7825. Min Act: -0.0000

Data Index: 1366082 (Python Code)

Max Activating Token Index: 176

Text #19

Max Range: 2.8797. Min Range: -2.8797

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1348838 (C4 (Web Text))

Max Activating Token Index: 782