Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3035 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0663. Min Act: -0.0001

Data Index: 829199 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0512. Min Act: -0.0001

Data Index: 772890 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0625. Min Act: -0.0001

Data Index: 60901 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1343675 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0619. Min Act: -0.0001

Data Index: 762790 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0604. Min Act: -0.0001

Data Index: 284627 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0639. Min Act: -0.0001

Data Index: 239657 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1359306 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1249140 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1088233 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1162707 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1253149 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0591. Min Act: -0.0001

Data Index: 491043 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0590. Min Act: -0.0001

Data Index: 787406 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0591. Min Act: -0.0001

Data Index: 450764 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0565. Min Act: -0.0001

Data Index: 198183 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1323268 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0580. Min Act: -0.0001

Data Index: 592044 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0584. Min Act: -0.0001

Data Index: 360665 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1139078 (C4 (Web Text))

Max Activating Token Index: 547