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

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

Neuron 1442 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.5061. Min Act: -0.0004

Data Index: 484009 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3983. Min Act: -0.0004

Data Index: 48516 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4006. Min Act: -0.0004

Data Index: 619388 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4025. Min Act: -0.0004

Data Index: 892608 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3744. Min Act: -0.0004

Data Index: 446456 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4155. Min Act: -0.0004

Data Index: 912078 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3554. Min Act: -0.0004

Data Index: 1245984 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3821. Min Act: -0.0004

Data Index: 930810 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3302. Min Act: -0.0004

Data Index: 598012 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3803. Min Act: -0.0004

Data Index: 949375 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3411. Min Act: -0.0004

Data Index: 607480 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3483. Min Act: -0.0004

Data Index: 207453 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3981. Min Act: -0.0004

Data Index: 876239 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3212. Min Act: -0.0004

Data Index: 482877 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3532. Min Act: -0.0004

Data Index: 658565 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3657. Min Act: -0.0004

Data Index: 1041203 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3788. Min Act: -0.0004

Data Index: 77891 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.2694. Min Act: -0.0004

Data Index: 1064567 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3464. Min Act: -0.0004

Data Index: 953181 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3442. Min Act: -0.0004

Data Index: 952475 (C4 (Web Text))

Max Activating Token Index: 807