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

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

Neuron 1274 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: 0.0510. Min Range: -0.0510

Max Act: 0.0504. Min Act: -0.0002

Data Index: 766953 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0504. Min Act: -0.0002

Data Index: 149654 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0497. Min Act: -0.0002

Data Index: 344832 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0454. Min Act: -0.0002

Data Index: 417591 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1096891 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0002

Data Index: 103662 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0482. Min Act: -0.0002

Data Index: 80287 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0474. Min Act: -0.0002

Data Index: 517000 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1063883 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1015786 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0472. Min Act: -0.0002

Data Index: 365659 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0468. Min Act: -0.0002

Data Index: 640141 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0453. Min Act: -0.0002

Data Index: 666422 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0466. Min Act: -0.0002

Data Index: 483282 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1130375 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0443. Min Act: -0.0002

Data Index: 534372 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0458. Min Act: -0.0002

Data Index: 528685 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0458. Min Act: -0.0002

Data Index: 687435 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0458. Min Act: -0.0002

Data Index: 435178 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1244685 (C4 (Web Text))

Max Activating Token Index: 9