Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2050 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1533511 (Python Code)

Max Activating Token Index: 694

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1419885 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1087. Min Act: -0.0001

Data Index: 232369 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 366598 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1473714 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1441557 (Python Code)

Max Activating Token Index: 727

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1636143 (Python Code)

Max Activating Token Index: 212

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1614841 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0929. Min Act: -0.0001

Data Index: 225407 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1407751 (Python Code)

Max Activating Token Index: 194

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1422610 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1011261 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1636575 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1310526 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1550595 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1519008 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0855. Min Act: -0.0001

Data Index: 57403 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1391862 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1635612 (Python Code)

Max Activating Token Index: 609

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0865. Min Act: -0.0001

Data Index: 442553 (C4 (Web Text))

Max Activating Token Index: 920