Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 185 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1081. Min Act: -0.0004

Data Index: 1237769 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1031. Min Act: -0.0003

Data Index: 76602 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1025. Min Act: -0.0004

Data Index: 394487 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0925. Min Act: -0.0003

Data Index: 779749 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0961. Min Act: -0.0003

Data Index: 1155937 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0941. Min Act: -0.0004

Data Index: 581141 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0938. Min Act: -0.0004

Data Index: 20317 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0931. Min Act: -0.0004

Data Index: 642689 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0901. Min Act: -0.0003

Data Index: 347646 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0922. Min Act: -0.0003

Data Index: 944617 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0957. Min Act: -0.0003

Data Index: 238726 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1201345 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0905. Min Act: -0.0003

Data Index: 1252623 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0877. Min Act: -0.0003

Data Index: 538208 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0857. Min Act: -0.0002

Data Index: 392928 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1322554 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1271425 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0815. Min Act: -0.0003

Data Index: 586253 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0852. Min Act: -0.0003

Data Index: 835602 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0841. Min Act: -0.0003

Data Index: 765045 (C4 (Web Text))

Max Activating Token Index: 931