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

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

Neuron 706 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0078. Min Act: -0.0005

Data Index: 31257 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0069. Min Act: -0.0006

Data Index: 683984 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1042858 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0066. Min Act: -0.0006

Data Index: 158959 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 130915 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1265708 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0066. Min Act: -0.0006

Data Index: 568803 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1168319 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 61470 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 747005 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1139839 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1371274 (Python Code)

Max Activating Token Index: 859

Text #12

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1116169 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0059. Min Act: -0.0006

Data Index: 127788 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0059. Min Act: -0.0006

Data Index: 635686 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1014959 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0060. Min Act: -0.0006

Data Index: 636826 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0058. Min Act: -0.0006

Data Index: 791517 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1582771 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1288280 (C4 (Web Text))

Max Activating Token Index: 495