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

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

Neuron 680 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1639505 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1608504 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1578790 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1456256 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1457868 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1444331 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1579620 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1441334 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1460304 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1629201 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1384006 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1625640 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1586514 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1406326 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1459331 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1550061 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1449602 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1553610 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0101. Min Act: -0.0006

Data Index: 142906 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0099. Min Act: -0.0005

Data Index: 1565205 (Python Code)

Max Activating Token Index: 3