Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2309 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1635132 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1548877 (Python Code)

Max Activating Token Index: 690

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1499400 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1465431 (Python Code)

Max Activating Token Index: 990

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1436966 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1512718 (Python Code)

Max Activating Token Index: 966

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1324076 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1169191 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1635661 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1623614 (Python Code)

Max Activating Token Index: 203

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1631092 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1455463 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1601495 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1570970 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0118. Min Act: -0.0004

Data Index: 633095 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1385521 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0118. Min Act: -0.0003

Data Index: 252067 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1363728 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0113. Min Act: -0.0003

Data Index: 825098 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1638629 (Python Code)

Max Activating Token Index: 734