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

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

Neuron 177 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: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1185361 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0005

Data Index: 823410 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1500990 (Python Code)

Max Activating Token Index: 575

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1238406 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 317405 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0050. Min Act: -0.0006

Data Index: 729265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0006

Data Index: 100020 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0049. Min Act: -0.0005

Data Index: 954373 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1532845 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1571292 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1382144 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0006

Data Index: 119319 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 187535 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0046. Min Act: -0.0006

Data Index: 261492 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0005

Data Index: 1071371 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1344481 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0006

Data Index: 685924 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0044. Min Act: -0.0006

Data Index: 1412174 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0006

Data Index: 601712 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0045. Min Act: -0.0006

Data Index: 881891 (C4 (Web Text))

Max Activating Token Index: 681