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

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

Neuron 4903 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: 1.6156. Min Range: -1.6156

Max Act: 1.5816. Min Act: -0.0000

Data Index: 962777 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.6156. Min Act: -0.0001

Data Index: 1113196 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5898. Min Act: -0.0001

Data Index: 1623751 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4856. Min Act: -0.0001

Data Index: 1607262 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4396. Min Act: -0.0001

Data Index: 381202 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5210. Min Act: -0.0001

Data Index: 372037 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4111. Min Act: -0.0001

Data Index: 123565 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4837. Min Act: -0.0001

Data Index: 1566616 (Python Code)

Max Activating Token Index: 752

Text #8

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4822. Min Act: -0.0001

Data Index: 1502017 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4745. Min Act: -0.0000

Data Index: 343032 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4819. Min Act: -0.0001

Data Index: 1369964 (Python Code)

Max Activating Token Index: 529

Text #11

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4623. Min Act: -0.0000

Data Index: 433908 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.2605. Min Act: -0.0001

Data Index: 302386 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4407. Min Act: -0.0001

Data Index: 1582888 (Python Code)

Max Activating Token Index: 682

Text #14

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4091. Min Act: -0.0001

Data Index: 1532073 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.3929. Min Act: -0.0000

Data Index: 126722 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1628808 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4385. Min Act: -0.0000

Data Index: 1107280 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.4094. Min Act: -0.0001

Data Index: 216310 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.3318. Min Act: -0.0001

Data Index: 1396016 (Python Code)

Max Activating Token Index: 207