Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 365 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0002

Data Index: 547869 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1044. Min Act: -0.0002

Data Index: 680168 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0979. Min Act: -0.0002

Data Index: 172224 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0927. Min Act: -0.0002

Data Index: 95530 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1228700 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0920. Min Act: -0.0002

Data Index: 267303 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0952. Min Act: -0.0002

Data Index: 513436 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0980. Min Act: -0.0002

Data Index: 520612 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1298740 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1326367 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1256762 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1348235 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1288265 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0848. Min Act: -0.0002

Data Index: 106492 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1027823 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0964. Min Act: -0.0002

Data Index: 205152 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0897. Min Act: -0.0002

Data Index: 880299 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1126610 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1103289 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0863. Min Act: -0.0002

Data Index: 645153 (C4 (Web Text))

Max Activating Token Index: 178