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

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

Neuron 4523 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1415350 (Python Code)

Max Activating Token Index: 289

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1609741 (Python Code)

Max Activating Token Index: 771

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1463100 (Python Code)

Max Activating Token Index: 201

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1404742 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1547248 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1400932 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1373767 (Python Code)

Max Activating Token Index: 997

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0809. Min Act: -0.0001

Data Index: 697576 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1583182 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1483968 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1521814 (Python Code)

Max Activating Token Index: 592

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1543585 (Python Code)

Max Activating Token Index: 872

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1651356 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1606173 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1559137 (Python Code)

Max Activating Token Index: 1010

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1602085 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1600593 (Python Code)

Max Activating Token Index: 582

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1571968 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1369200 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1559501 (Python Code)

Max Activating Token Index: 597