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

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

Neuron 1961 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0002

Data Index: 649336 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1083594 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1102949 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1247826 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0524. Min Act: -0.0002

Data Index: 426547 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0521. Min Act: -0.0002

Data Index: 308203 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0524. Min Act: -0.0002

Data Index: 119131 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1078160 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0539. Min Act: -0.0002

Data Index: 16260 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0479. Min Act: -0.0002

Data Index: 224431 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1355976 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0515. Min Act: -0.0002

Data Index: 585024 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0455. Min Act: -0.0002

Data Index: 587942 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1292851 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0499. Min Act: -0.0002

Data Index: 846089 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0514. Min Act: -0.0002

Data Index: 255362 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1101919 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0458. Min Act: -0.0002

Data Index: 166343 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0488. Min Act: -0.0002

Data Index: 143130 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1194622 (C4 (Web Text))

Max Activating Token Index: 703