Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4446 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1489389 (Python Code)

Max Activating Token Index: 939

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1397973 (Python Code)

Max Activating Token Index: 831

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1177528 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1544633 (Python Code)

Max Activating Token Index: 899

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1478787 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0127. Min Act: -0.0002

Data Index: 135268 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1613300 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1639490 (Python Code)

Max Activating Token Index: 841

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1508379 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1382233 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1261733 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1300590 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1556675 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1588530 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1383133 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0113. Min Act: -0.0002

Data Index: 77534 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0125. Min Act: -0.0002

Data Index: 381445 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1638063 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1452005 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1364347 (Python Code)

Max Activating Token Index: 956