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

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

Neuron 4932 in Layer 0

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: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0001

Data Index: 986081 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1272432 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1075645 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1393606 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0992. Min Act: -0.0001

Data Index: 67554 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1091229 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0974. Min Act: -0.0001

Data Index: 129534 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1485505 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0987. Min Act: -0.0001

Data Index: 399143 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0963. Min Act: -0.0001

Data Index: 931920 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0951. Min Act: -0.0001

Data Index: 109639 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0937. Min Act: -0.0001

Data Index: 634702 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0948. Min Act: -0.0001

Data Index: 165309 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0950. Min Act: -0.0001

Data Index: 510423 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0958. Min Act: -0.0001

Data Index: 65634 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1424345 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1206791 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1391700 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1652693 (Python Code)

Max Activating Token Index: 837

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0924. Min Act: -0.0001

Data Index: 446201 (C4 (Web Text))

Max Activating Token Index: 959