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

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

Neuron 6106 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0760. Min Act: -0.0001

Data Index: 541232 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1180653 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0834. Min Act: -0.0001

Data Index: 507545 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0710. Min Act: -0.0001

Data Index: 709914 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0769. Min Act: -0.0001

Data Index: 104238 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0685. Min Act: -0.0002

Data Index: 463897 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1350326 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1213580 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0653. Min Act: -0.0001

Data Index: 195599 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0692. Min Act: -0.0001

Data Index: 335312 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0680. Min Act: -0.0001

Data Index: 697560 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0605. Min Act: -0.0001

Data Index: 266478 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0645. Min Act: -0.0001

Data Index: 139289 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0569. Min Act: -0.0001

Data Index: 758952 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1634215 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0621. Min Act: -0.0002

Data Index: 223701 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1212023 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0539. Min Act: -0.0001

Data Index: 702181 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0526. Min Act: -0.0001

Data Index: 243382 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1180002 (C4 (Web Text))

Max Activating Token Index: 595