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

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

Neuron 1902 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: 0.1022. Min Range: -0.1022

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1412982 (Python Code)

Max Activating Token Index: 839

Text #1

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1404052 (Python Code)

Max Activating Token Index: 819

Text #2

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1472782 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1507977 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1507914 (Python Code)

Max Activating Token Index: 321

Text #5

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1530811 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1575894 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1459485 (Python Code)

Max Activating Token Index: 442

Text #8

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0974. Min Act: -0.0002

Data Index: 30717 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1515081 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1527240 (Python Code)

Max Activating Token Index: 556

Text #11

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1202202 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1485248 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1651406 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1444099 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1540454 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1415465 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1527132 (Python Code)

Max Activating Token Index: 519

Text #18

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1444394 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1362092 (Python Code)

Max Activating Token Index: 651