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

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

Neuron 1989 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0930. Min Act: -0.0001

Data Index: 174198 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0915. Min Act: -0.0001

Data Index: 87453 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0876. Min Act: -0.0001

Data Index: 924425 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0812. Min Act: -0.0001

Data Index: 855530 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0753. Min Act: -0.0001

Data Index: 204775 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0771. Min Act: -0.0001

Data Index: 265337 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0744. Min Act: -0.0001

Data Index: 925353 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0770. Min Act: -0.0001

Data Index: 87306 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0702. Min Act: -0.0001

Data Index: 383714 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0702. Min Act: -0.0001

Data Index: 438068 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1327892 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0718. Min Act: -0.0001

Data Index: 590325 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0710. Min Act: -0.0001

Data Index: 568381 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0640. Min Act: -0.0001

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0692. Min Act: -0.0001

Data Index: 432579 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1226517 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0644. Min Act: -0.0001

Data Index: 843733 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1236061 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0639. Min Act: -0.0001

Data Index: 83239 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0613. Min Act: -0.0001

Data Index: 71040 (C4 (Web Text))

Max Activating Token Index: 573