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

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

Neuron 5956 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7791. Min Act: -0.0002

Data Index: 242038 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7050. Min Act: -0.0001

Data Index: 194197 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7649. Min Act: -0.0001

Data Index: 1126480 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6976. Min Act: -0.0001

Data Index: 266314 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6771. Min Act: -0.0001

Data Index: 1245202 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7036. Min Act: -0.0001

Data Index: 43277 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7182. Min Act: -0.0001

Data Index: 1312822 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6732. Min Act: -0.0001

Data Index: 1156585 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6922. Min Act: -0.0001

Data Index: 818883 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5810. Min Act: -0.0001

Data Index: 604643 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6619. Min Act: -0.0001

Data Index: 237526 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6206. Min Act: -0.0001

Data Index: 226672 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6043. Min Act: -0.0001

Data Index: 258343 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5959. Min Act: -0.0001

Data Index: 227643 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6604. Min Act: -0.0001

Data Index: 664219 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5361. Min Act: -0.0001

Data Index: 345233 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6397. Min Act: -0.0001

Data Index: 779013 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7130. Min Act: -0.0001

Data Index: 677457 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6045. Min Act: -0.0001

Data Index: 1604010 (Python Code)

Max Activating Token Index: 619

Text #19

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5179. Min Act: -0.0001

Data Index: 1308096 (C4 (Web Text))

Max Activating Token Index: 163