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

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

Neuron 1066 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: 0.4586. Min Range: -0.4586

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1254167 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.4586. Min Act: -0.0000

Data Index: 606686 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1036122 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1101452 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3904. Min Act: -0.0000

Data Index: 541842 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.4025. Min Act: -0.0000

Data Index: 37674 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1207082 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1038746 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3543. Min Act: -0.0000

Data Index: 857659 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1160218 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1025888 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3332. Min Act: -0.0001

Data Index: 1214393 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3873. Min Act: -0.0000

Data Index: 151728 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3454. Min Act: -0.0000

Data Index: 338810 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.2971. Min Act: -0.0001

Data Index: 436445 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3170. Min Act: -0.0001

Data Index: 809737 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1182645 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3322. Min Act: -0.0001

Data Index: 493960 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3003. Min Act: -0.0000

Data Index: 722942 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.4586. Min Range: -0.4586

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1076221 (C4 (Web Text))

Max Activating Token Index: 335