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

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

Neuron 5456 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3937. Min Act: -0.0001

Data Index: 1066944 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3452. Min Act: -0.0000

Data Index: 525189 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3420. Min Act: -0.0000

Data Index: 544720 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3417. Min Act: -0.0001

Data Index: 1004491 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3537. Min Act: -0.0000

Data Index: 92261 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2954. Min Act: -0.0001

Data Index: 585800 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2636. Min Act: -0.0001

Data Index: 737892 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3292. Min Act: -0.0000

Data Index: 796664 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3018. Min Act: -0.0000

Data Index: 258096 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3122. Min Act: -0.0000

Data Index: 819606 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2806. Min Act: -0.0000

Data Index: 738502 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2652. Min Act: -0.0000

Data Index: 392081 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2666. Min Act: -0.0000

Data Index: 397984 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2838. Min Act: -0.0001

Data Index: 814253 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2813. Min Act: -0.0000

Data Index: 728635 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1318941 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2948. Min Act: -0.0001

Data Index: 284416 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2782. Min Act: -0.0000

Data Index: 313124 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1298432 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2817. Min Act: -0.0001

Data Index: 572009 (C4 (Web Text))

Max Activating Token Index: 381