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

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

Neuron 2484 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.9337. Min Act: -0.0001

Data Index: 921562 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1052330 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.9022. Min Act: -0.0001

Data Index: 1146089 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.8522. Min Act: -0.0000

Data Index: 554766 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1302008 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.7172. Min Act: -0.0001

Data Index: 891506 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1301695 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.7721. Min Act: -0.0000

Data Index: 417937 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.7186. Min Act: -0.0001

Data Index: 932451 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.7078. Min Act: -0.0000

Data Index: 285242 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6996. Min Act: -0.0000

Data Index: 751679 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6991. Min Act: -0.0001

Data Index: 420608 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.7212. Min Act: -0.0000

Data Index: 473393 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6630. Min Act: -0.0001

Data Index: 64640 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1337865 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1396074 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6723. Min Act: -0.0000

Data Index: 243590 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6638. Min Act: -0.0001

Data Index: 959045 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6762. Min Act: -0.0001

Data Index: 661912 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.9337. Min Range: -0.9337

Max Act: 0.6414. Min Act: -0.0000

Data Index: 971178 (C4 (Web Text))

Max Activating Token Index: 592