Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 957 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.9922. Min Act: -0.0005

Data Index: 314822 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8838. Min Act: -0.0005

Data Index: 837331 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.8869. Min Act: -0.0005

Data Index: 1422031 (Python Code)

Max Activating Token Index: 245

Text #3

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6050. Min Act: -0.0005

Data Index: 1318778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.6056. Min Act: -0.0005

Data Index: 422869 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.4787. Min Act: -0.0005

Data Index: 780700 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.5025. Min Act: -0.0005

Data Index: 1105038 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.4154. Min Act: -0.0005

Data Index: 1388406 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.3325. Min Act: -0.0005

Data Index: 47878 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.3114. Min Act: -0.0005

Data Index: 1572470 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.2569. Min Act: -0.0005

Data Index: 1609712 (Python Code)

Max Activating Token Index: 193

Text #11

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.2550. Min Act: -0.0005

Data Index: 493105 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.1861. Min Act: -0.0005

Data Index: 1281704 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.1945. Min Act: -0.0005

Data Index: 1411172 (Python Code)

Max Activating Token Index: 227

Text #14

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.3415. Min Act: -0.0005

Data Index: 901669 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.2360. Min Act: -0.0005

Data Index: 1427905 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.1940. Min Act: -0.0005

Data Index: 1383581 (Python Code)

Max Activating Token Index: 928

Text #17

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.2002. Min Act: -0.0005

Data Index: 1453385 (Python Code)

Max Activating Token Index: 237

Text #18

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.1006. Min Act: -0.0005

Data Index: 366062 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.9922. Min Range: -0.9922

Max Act: 0.1509. Min Act: -0.0005

Data Index: 451272 (C4 (Web Text))

Max Activating Token Index: 327