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

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

Neuron 3456 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1408051 (Python Code)

Max Activating Token Index: 990

Text #1

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1360083 (Python Code)

Max Activating Token Index: 690

Text #2

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0928. Min Act: -0.0000

Data Index: 39206 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1459059 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1539788 (Python Code)

Max Activating Token Index: 415

Text #5

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1507862 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1316026 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0383. Min Act: -0.0000

Data Index: 707369 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1111437 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9774. Min Act: -0.0000

Data Index: 99204 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1093455 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1341037 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1387515 (Python Code)

Max Activating Token Index: 848

Text #13

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8949. Min Act: -0.0000

Data Index: 568035 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1380222 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8146. Min Act: -0.0000

Data Index: 118087 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8585. Min Act: -0.0000

Data Index: 530781 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8123. Min Act: -0.0000

Data Index: 671873 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8309. Min Act: -0.0000

Data Index: 566746 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1566418 (Python Code)

Max Activating Token Index: 638