Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.1031. Min Act: -0.0000

Data Index: 835942 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.0493. Min Act: -0.0000

Data Index: 196301 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1034150 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1239635 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9163. Min Act: -0.0000

Data Index: 201146 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9127. Min Act: -0.0000

Data Index: 40866 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9052. Min Act: -0.0000

Data Index: 568163 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9289. Min Act: -0.0000

Data Index: 736890 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1120715 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8657. Min Act: -0.0000

Data Index: 628601 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8701. Min Act: -0.0000

Data Index: 329346 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8971. Min Act: -0.0000

Data Index: 778341 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8956. Min Act: -0.0000

Data Index: 529640 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8431. Min Act: -0.0000

Data Index: 147402 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8586. Min Act: -0.0000

Data Index: 937871 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8226. Min Act: -0.0000

Data Index: 511860 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1120110 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1150191 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8379. Min Act: -0.0000

Data Index: 687351 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8881. Min Act: -0.0000

Data Index: 44988 (C4 (Web Text))

Max Activating Token Index: 842