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

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

Neuron 5028 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: 2.5526. Min Range: -2.5526

Max Act: 2.5526. Min Act: -0.0000

Data Index: 143332 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.4414. Min Act: -0.0000

Data Index: 1156251 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.3016. Min Act: -0.0000

Data Index: 217669 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.4132. Min Act: -0.0000

Data Index: 27438 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.4160. Min Act: -0.0000

Data Index: 633325 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.3916. Min Act: -0.0000

Data Index: 59127 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.3178. Min Act: -0.0000

Data Index: 99454 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.3001. Min Act: -0.0000

Data Index: 366981 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.2976. Min Act: -0.0000

Data Index: 1074496 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.4155. Min Act: -0.0000

Data Index: 204032 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.2969. Min Act: -0.0000

Data Index: 932823 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.2794. Min Act: -0.0000

Data Index: 527502 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.2655. Min Act: -0.0000

Data Index: 681801 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.0782. Min Act: -0.0000

Data Index: 1010718 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.1967. Min Act: -0.0000

Data Index: 190666 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.0407. Min Act: -0.0000

Data Index: 705435 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.1628. Min Act: -0.0000

Data Index: 559081 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.0843. Min Act: -0.0000

Data Index: 337077 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.0738. Min Act: -0.0000

Data Index: 481516 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 2.5526. Min Range: -2.5526

Max Act: 2.1929. Min Act: -0.0000

Data Index: 1300571 (C4 (Web Text))

Max Activating Token Index: 378