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

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

Neuron 3936 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5992. Min Act: -0.0000

Data Index: 946438 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5302. Min Act: -0.0000

Data Index: 294096 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4948. Min Act: -0.0000

Data Index: 749168 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4749. Min Act: -0.0000

Data Index: 405685 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4901. Min Act: -0.0000

Data Index: 885132 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1066773 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4666. Min Act: -0.0000

Data Index: 711351 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4612. Min Act: -0.0000

Data Index: 416212 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4310. Min Act: -0.0000

Data Index: 491179 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1004209 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3949. Min Act: -0.0000

Data Index: 246954 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4352. Min Act: -0.0000

Data Index: 316408 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4105. Min Act: -0.0000

Data Index: 942080 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3873. Min Act: -0.0000

Data Index: 781089 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4063. Min Act: -0.0000

Data Index: 621042 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1160225 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1312169 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1135231 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3989. Min Act: -0.0000

Data Index: 292368 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3783. Min Act: -0.0000

Data Index: 504427 (C4 (Web Text))

Max Activating Token Index: 319