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

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

Neuron 3803 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2514. Min Act: -0.0000

Data Index: 655216 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2525. Min Act: -0.0000

Data Index: 835060 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1270477 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2526. Min Act: -0.0000

Data Index: 252617 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2383. Min Act: -0.0000

Data Index: 195241 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2065. Min Act: -0.0000

Data Index: 826514 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2094. Min Act: -0.0000

Data Index: 516787 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1935. Min Act: -0.0000

Data Index: 483264 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2092. Min Act: -0.0000

Data Index: 56543 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2057. Min Act: -0.0000

Data Index: 444033 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1312514 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1302568 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1287062 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1095861 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1589468 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1893. Min Act: -0.0000

Data Index: 280231 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1450360 (Python Code)

Max Activating Token Index: 763

Text #17

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1562808 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1674. Min Act: -0.0000

Data Index: 208585 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1991. Min Act: -0.0000

Data Index: 458689 (C4 (Web Text))

Max Activating Token Index: 359