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

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

Neuron 4174 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1585548 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0658. Min Act: -0.0001

Data Index: 154693 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1634545 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1628228 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1613465 (Python Code)

Max Activating Token Index: 958

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1316488 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1603289 (Python Code)

Max Activating Token Index: 226

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0570. Min Act: -0.0001

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1047523 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1537332 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0576. Min Act: -0.0001

Data Index: 392967 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0621. Min Act: -0.0001

Data Index: 650687 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0568. Min Act: -0.0001

Data Index: 738587 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0559. Min Act: -0.0001

Data Index: 161863 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0557. Min Act: -0.0001

Data Index: 419882 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0568. Min Act: -0.0001

Data Index: 699562 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1486051 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0500. Min Act: -0.0001

Data Index: 888452 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0536. Min Act: -0.0001

Data Index: 227027 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1092438 (C4 (Web Text))

Max Activating Token Index: 190