Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9993. Min Act: -0.0001

Data Index: 560525 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9008. Min Act: -0.0001

Data Index: 382961 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7947. Min Act: -0.0001

Data Index: 464655 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8084. Min Act: -0.0001

Data Index: 9209 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8367. Min Act: -0.0001

Data Index: 363063 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8222. Min Act: -0.0001

Data Index: 1276380 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7561. Min Act: -0.0001

Data Index: 662200 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7404. Min Act: -0.0001

Data Index: 571018 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7607. Min Act: -0.0001

Data Index: 602712 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7184. Min Act: -0.0001

Data Index: 626439 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7711. Min Act: -0.0001

Data Index: 458665 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7607. Min Act: -0.0001

Data Index: 385209 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7374. Min Act: -0.0001

Data Index: 531881 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7265. Min Act: -0.0001

Data Index: 214051 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6815. Min Act: -0.0001

Data Index: 70761 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6306. Min Act: -0.0001

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6870. Min Act: -0.0001

Data Index: 905701 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7086. Min Act: -0.0001

Data Index: 1307775 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6624. Min Act: -0.0001

Data Index: 402621 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6648. Min Act: -0.0001

Data Index: 189279 (C4 (Web Text))

Max Activating Token Index: 35