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

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

Neuron 761 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1483641 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0125. Min Act: -0.0005

Data Index: 1390281 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1467482 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1559773 (Python Code)

Max Activating Token Index: 415

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1391817 (Python Code)

Max Activating Token Index: 782

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1419257 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1397656 (Python Code)

Max Activating Token Index: 703

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1622852 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1392861 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1468477 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1497759 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1607364 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1099529 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1656735 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0005

Data Index: 1495056 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1582342 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1535622 (Python Code)

Max Activating Token Index: 491

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1611040 (Python Code)

Max Activating Token Index: 699

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1568344 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1409402 (Python Code)

Max Activating Token Index: 825