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

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

Neuron 5833 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0759. Min Act: -0.0002

Data Index: 983211 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0746. Min Act: -0.0002

Data Index: 731486 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0677. Min Act: -0.0002

Data Index: 690225 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0620. Min Act: -0.0002

Data Index: 155228 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0644. Min Act: -0.0002

Data Index: 928994 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0625. Min Act: -0.0002

Data Index: 171069 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1345944 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0591. Min Act: -0.0002

Data Index: 249518 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0573. Min Act: -0.0002

Data Index: 475753 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0569. Min Act: -0.0002

Data Index: 391538 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0565. Min Act: -0.0002

Data Index: 776322 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0542. Min Act: -0.0002

Data Index: 822036 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0560. Min Act: -0.0002

Data Index: 845015 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0560. Min Act: -0.0002

Data Index: 872888 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0534. Min Act: -0.0002

Data Index: 238385 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1274960 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0573. Min Act: -0.0002

Data Index: 38197 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0551. Min Act: -0.0002

Data Index: 910692 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1185530 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0562. Min Act: -0.0002

Data Index: 264399 (C4 (Web Text))

Max Activating Token Index: 316