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

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

Neuron 2008 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.5608. Min Act: -0.0000

Data Index: 780607 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1218842 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3467. Min Act: -0.0000

Data Index: 136783 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3687. Min Act: -0.0000

Data Index: 339001 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3567. Min Act: -0.0000

Data Index: 99329 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3231. Min Act: -0.0000

Data Index: 104968 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1262852 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3348. Min Act: -0.0000

Data Index: 164521 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3217. Min Act: -0.0000

Data Index: 506474 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3147. Min Act: -0.0000

Data Index: 159898 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1245355 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3147. Min Act: -0.0000

Data Index: 256007 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2880. Min Act: -0.0000

Data Index: 887754 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2976. Min Act: -0.0000

Data Index: 475053 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1080103 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2696. Min Act: -0.0000

Data Index: 957347 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2856. Min Act: 0.0000

Data Index: 632808 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1086781 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2821. Min Act: -0.0000

Data Index: 591030 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.2721. Min Act: -0.0000

Data Index: 878616 (C4 (Web Text))

Max Activating Token Index: 791