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

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

Neuron 1993 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: 0.0054. Min Range: -0.0054

Max Act: 0.0054. Min Act: -0.0002

Data Index: 729365 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0002

Data Index: 694839 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1337450 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1410750 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0046. Min Act: -0.0002

Data Index: 19982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1397049 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1579174 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0038. Min Act: -0.0002

Data Index: 210864 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0037. Min Act: -0.0002

Data Index: 589605 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0037. Min Act: -0.0002

Data Index: 995019 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1389125 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0036. Min Act: -0.0002

Data Index: 976616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1058809 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1277211 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0034. Min Act: -0.0002

Data Index: 255895 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1532106 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0035. Min Act: -0.0002

Data Index: 520689 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0033. Min Act: -0.0002

Data Index: 351625 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0033. Min Act: -0.0002

Data Index: 1270341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0054. Min Range: -0.0054

Max Act: 0.0034. Min Act: -0.0002

Data Index: 234503 (C4 (Web Text))

Max Activating Token Index: 1023