Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3117 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3653. Min Act: -0.0000

Data Index: 102097 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3201. Min Act: -0.0001

Data Index: 692494 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1314434 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3254. Min Act: -0.0000

Data Index: 346157 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3250. Min Act: -0.0001

Data Index: 659960 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3000. Min Act: -0.0000

Data Index: 103994 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2999. Min Act: -0.0000

Data Index: 689233 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2729. Min Act: -0.0001

Data Index: 737003 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2920. Min Act: -0.0000

Data Index: 941884 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2915. Min Act: -0.0001

Data Index: 524842 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2848. Min Act: -0.0001

Data Index: 706244 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2833. Min Act: -0.0001

Data Index: 1203615 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2737. Min Act: -0.0000

Data Index: 157672 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.3016. Min Act: -0.0000

Data Index: 618397 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1323830 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2802. Min Act: -0.0000

Data Index: 999939 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1151541 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2751. Min Act: -0.0000

Data Index: 958807 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2650. Min Act: -0.0001

Data Index: 851474 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.3653. Min Range: -0.3653

Max Act: 0.2609. Min Act: -0.0000

Data Index: 589035 (C4 (Web Text))

Max Activating Token Index: 343