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

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

Neuron 5958 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: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1130490 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1390629 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1186997 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1462747 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1429059 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1512534 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1370764 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1576770 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1528092 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1636020 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1481739 (Python Code)

Max Activating Token Index: 531

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1377711 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1457501 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1437332 (Python Code)

Max Activating Token Index: 382

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1425671 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1517519 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1494016 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1454320 (Python Code)

Max Activating Token Index: 482

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1488719 (Python Code)

Max Activating Token Index: 962

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1436002 (Python Code)

Max Activating Token Index: 59