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

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

Neuron 4565 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.7084. Min Act: -0.0000

Data Index: 490272 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6552. Min Act: -0.0001

Data Index: 909141 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6576. Min Act: -0.0000

Data Index: 89310 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6384. Min Act: -0.0001

Data Index: 413227 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6531. Min Act: -0.0000

Data Index: 161939 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6294. Min Act: -0.0001

Data Index: 921227 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6125. Min Act: -0.0000

Data Index: 284511 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1326370 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1136079 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6187. Min Act: -0.0000

Data Index: 842743 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5078. Min Act: -0.0000

Data Index: 957739 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5800. Min Act: -0.0000

Data Index: 313198 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5777. Min Act: -0.0000

Data Index: 218620 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1012043 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5743. Min Act: -0.0000

Data Index: 538498 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5477. Min Act: -0.0001

Data Index: 488373 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5418. Min Act: -0.0001

Data Index: 200851 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5975. Min Act: -0.0000

Data Index: 850194 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5853. Min Act: -0.0000

Data Index: 507176 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5483. Min Act: -0.0000

Data Index: 995525 (C4 (Web Text))

Max Activating Token Index: 109