Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4770 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6888. Min Act: -0.0000

Data Index: 267042 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6369. Min Act: -0.0000

Data Index: 341280 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6535. Min Act: -0.0000

Data Index: 304810 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6400. Min Act: -0.0000

Data Index: 801837 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6244. Min Act: -0.0000

Data Index: 6198 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1141261 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6303. Min Act: -0.0000

Data Index: 594950 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6284. Min Act: -0.0000

Data Index: 483142 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6734. Min Act: -0.0000

Data Index: 860860 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6769. Min Act: -0.0000

Data Index: 684091 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6200. Min Act: -0.0000

Data Index: 846392 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6241. Min Act: -0.0000

Data Index: 825698 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6697. Min Act: -0.0000

Data Index: 605975 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6342. Min Act: -0.0000

Data Index: 716989 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1024982 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6562. Min Act: -0.0000

Data Index: 600298 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5773. Min Act: -0.0000

Data Index: 282803 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6021. Min Act: -0.0000

Data Index: 220802 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1042265 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6038. Min Act: -0.0000

Data Index: 924410 (C4 (Web Text))

Max Activating Token Index: 640