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

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

Neuron 4672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1242248 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1392380 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1196254 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1373852 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0990. Min Act: -0.0000

Data Index: 560151 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1455366 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1452621 (Python Code)

Max Activating Token Index: 960

Text #7

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0168. Min Act: -0.0000

Data Index: 519547 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0871. Min Act: -0.0000

Data Index: 771909 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1527384 (Python Code)

Max Activating Token Index: 618

Text #10

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0348. Min Act: -0.0000

Data Index: 787253 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0114. Min Act: -0.0000

Data Index: 177820 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 1.6664. Min Range: -1.6664

Max Act: 0.9585. Min Act: -0.0000

Data Index: 695393 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1295937 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.6664. Min Range: -1.6664

Max Act: 0.9363. Min Act: -0.0000

Data Index: 831537 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.6664. Min Range: -1.6664

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1405253 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 1.6664. Min Range: -1.6664

Max Act: 0.9252. Min Act: -0.0000

Data Index: 386837 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.6664. Min Range: -1.6664

Max Act: 1.0162. Min Act: -0.0000

Data Index: 399991 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.6664. Min Range: -1.6664

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1263968 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.6664. Min Range: -1.6664

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1066783 (C4 (Web Text))

Max Activating Token Index: 164