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

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

Neuron 1440 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: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1606220 (Python Code)

Max Activating Token Index: 753

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1387481 (Python Code)

Max Activating Token Index: 434

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1517935 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1523058 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1597352 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1505549 (Python Code)

Max Activating Token Index: 269

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1553374 (Python Code)

Max Activating Token Index: 583

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1383232 (Python Code)

Max Activating Token Index: 788

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1562564 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1360666 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1008. Min Act: -0.0002

Data Index: 107982 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1432978 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1591767 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1365000 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1377247 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1618346 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1362744 (Python Code)

Max Activating Token Index: 438

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1588193 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1589112 (Python Code)

Max Activating Token Index: 706

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1542233 (Python Code)

Max Activating Token Index: 229