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

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

Neuron 2011 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.5685. Min Act: -0.0000

Data Index: 1150682 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.5375. Min Act: -0.0000

Data Index: 35081 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1338944 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.6669. Min Act: -0.0000

Data Index: 611495 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.6541. Min Act: -0.0000

Data Index: 733360 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.5199. Min Act: -0.0000

Data Index: 1327312 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.5037. Min Act: -0.0000

Data Index: 273445 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.4941. Min Act: -0.0000

Data Index: 1142590 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.5560. Min Act: -0.0000

Data Index: 671085 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.3412. Min Act: -0.0000

Data Index: 126757 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.5318. Min Act: -0.0000

Data Index: 177157 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.3295. Min Act: -0.0000

Data Index: 223164 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.3244. Min Act: -0.0000

Data Index: 25916 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.3845. Min Act: -0.0000

Data Index: 59175 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.3127. Min Act: -0.0000

Data Index: 415970 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.3782. Min Act: -0.0000

Data Index: 383749 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.4420. Min Act: -0.0000

Data Index: 813040 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.3548. Min Act: -0.0000

Data Index: 751571 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.2480. Min Act: -0.0000

Data Index: 734531 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 1.6669. Min Range: -1.6669

Max Act: 1.4330. Min Act: -0.0000

Data Index: 828957 (C4 (Web Text))

Max Activating Token Index: 887