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

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

Neuron 3611 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1436116 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1375888 (Python Code)

Max Activating Token Index: 765

Text #2

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1633586 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1540583 (Python Code)

Max Activating Token Index: 819

Text #4

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1400366 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1573066 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1440870 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1395350 (Python Code)

Max Activating Token Index: 43

Text #8

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1599740 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1395787 (Python Code)

Max Activating Token Index: 769

Text #10

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1569024 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1364656 (Python Code)

Max Activating Token Index: 525

Text #12

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1419893 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1429039 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1625768 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1644960 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1402265 (Python Code)

Max Activating Token Index: 313

Text #17

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1426294 (Python Code)

Max Activating Token Index: 876

Text #18

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1600664 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1511888 (Python Code)

Max Activating Token Index: 906