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

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

Neuron 3011 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0975. Min Range: -1.0975

Max Act: 1.0975. Min Act: 0.0000

Data Index: 798168 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.0975. Min Range: -1.0975

Max Act: 1.0926. Min Act: 0.0001

Data Index: 483424 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.8819. Min Act: 0.0000

Data Index: 381127 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.8676. Min Act: 0.0000

Data Index: 1114922 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.8293. Min Act: 0.0000

Data Index: 496337 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.8515. Min Act: -0.0000

Data Index: 430595 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1028277 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.8673. Min Act: -0.0000

Data Index: 527831 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.8376. Min Act: -0.0000

Data Index: 744153 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.7863. Min Act: 0.0001

Data Index: 1071070 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.7757. Min Act: -0.0000

Data Index: 456345 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.7117. Min Act: 0.0000

Data Index: 562284 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.7408. Min Act: 0.0000

Data Index: 1220302 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.6669. Min Act: -0.0000

Data Index: 657214 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1102182 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.7255. Min Act: -0.0000

Data Index: 379902 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.6912. Min Act: -0.0000

Data Index: 495219 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.6892. Min Act: -0.0000

Data Index: 283384 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.6709. Min Act: -0.0000

Data Index: 894641 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.0975. Min Range: -1.0975

Max Act: 0.6379. Min Act: -0.0000

Data Index: 180585 (C4 (Web Text))

Max Activating Token Index: 161