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

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

Neuron 1095 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: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1413583 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0138. Min Act: -0.0006

Data Index: 551088 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1111755 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0132. Min Act: -0.0006

Data Index: 351292 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1399134 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0129. Min Act: -0.0006

Data Index: 414596 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1218017 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1554665 (Python Code)

Max Activating Token Index: 279

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1641547 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1612411 (Python Code)

Max Activating Token Index: 556

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1029921 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1016857 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1585025 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0122. Min Act: -0.0006

Data Index: 400141 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1410368 (Python Code)

Max Activating Token Index: 765

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1634388 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1511335 (Python Code)

Max Activating Token Index: 236

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1460169 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1481486 (Python Code)

Max Activating Token Index: 308

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1403131 (Python Code)

Max Activating Token Index: 314