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

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

Neuron 2802 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0004

Data Index: 255627 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 613771 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 945658 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1193190 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1257502 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0003

Data Index: 117349 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1271204 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 907912 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 534493 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1004794 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 489409 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 543162 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 307848 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1176304 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 275620 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0004

Data Index: 340663 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 751865 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 523221 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 160684 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1140209 (C4 (Web Text))

Max Activating Token Index: 433