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

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

Neuron 4396 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: 0.4528. Min Range: -0.4528

Max Act: 0.4528. Min Act: -0.0002

Data Index: 888722 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.4370. Min Act: -0.0002

Data Index: 948001 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.4176. Min Act: -0.0002

Data Index: 734195 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3989. Min Act: -0.0001

Data Index: 1485893 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3806. Min Act: -0.0002

Data Index: 193616 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3843. Min Act: -0.0002

Data Index: 1418207 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3717. Min Act: -0.0002

Data Index: 615756 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3639. Min Act: -0.0002

Data Index: 1491707 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3654. Min Act: -0.0002

Data Index: 1621585 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3666. Min Act: -0.0002

Data Index: 1333509 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3571. Min Act: -0.0001

Data Index: 1522034 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3456. Min Act: -0.0002

Data Index: 1354891 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3530. Min Act: -0.0002

Data Index: 1179783 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3655. Min Act: -0.0001

Data Index: 1466695 (Python Code)

Max Activating Token Index: 164

Text #14

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3451. Min Act: -0.0002

Data Index: 438597 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1465342 (Python Code)

Max Activating Token Index: 771

Text #16

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3549. Min Act: -0.0002

Data Index: 1484894 (Python Code)

Max Activating Token Index: 795

Text #17

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3462. Min Act: -0.0002

Data Index: 1154888 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3460. Min Act: -0.0002

Data Index: 1308190 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.4528. Min Range: -0.4528

Max Act: 0.3433. Min Act: -0.0002

Data Index: 1246502 (C4 (Web Text))

Max Activating Token Index: 213