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

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

Neuron 1266 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.7848. Min Act: -0.0001

Data Index: 74113 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.5597. Min Act: -0.0000

Data Index: 666724 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.5246. Min Act: -0.0001

Data Index: 1265118 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.5616. Min Act: -0.0000

Data Index: 187332 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.5231. Min Act: -0.0001

Data Index: 1498287 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.5276. Min Act: -0.0001

Data Index: 31334 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.4010. Min Act: -0.0001

Data Index: 1487593 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.2843. Min Act: -0.0001

Data Index: 1192702 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.2813. Min Act: 0.0003

Data Index: 907181 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.2335. Min Act: -0.0000

Data Index: 202564 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1817. Min Act: -0.0000

Data Index: 257334 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1596. Min Act: -0.0000

Data Index: 115303 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1880. Min Act: -0.0000

Data Index: 544770 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1903. Min Act: -0.0000

Data Index: 602660 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1897. Min Act: -0.0001

Data Index: 867384 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1786. Min Act: -0.0001

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1838. Min Act: -0.0000

Data Index: 30070 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1667. Min Act: -0.0001

Data Index: 1472253 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1351402 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.7848. Min Range: -1.7848

Max Act: 1.1266. Min Act: -0.0000

Data Index: 970570 (C4 (Web Text))

Max Activating Token Index: 980