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

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

Neuron 387 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: 0.0071. Min Range: -0.0071

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1555166 (Python Code)

Max Activating Token Index: 651

Text #1

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0068. Min Act: -0.0006

Data Index: 966358 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0006

Data Index: 825030 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0006

Data Index: 979599 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1242097 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1132633 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1131238 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0058. Min Act: -0.0006

Data Index: 753062 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0054. Min Act: -0.0006

Data Index: 753436 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0058. Min Act: -0.0006

Data Index: 27506 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0058. Min Act: -0.0006

Data Index: 778988 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1530176 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0056. Min Act: -0.0006

Data Index: 377868 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1624608 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1021936 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1120596 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0054. Min Act: -0.0006

Data Index: 966707 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0053. Min Act: -0.0006

Data Index: 964144 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1578630 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0050. Min Act: -0.0006

Data Index: 296022 (C4 (Web Text))

Max Activating Token Index: 794