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

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

Neuron 669 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: 3.0874. Min Range: -3.0874

Max Act: 3.0874. Min Act: -0.0001

Data Index: 390855 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.9935. Min Act: -0.0001

Data Index: 1448054 (Python Code)

Max Activating Token Index: 932

Text #2

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.8675. Min Act: -0.0001

Data Index: 1108840 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 3.0874. Min Range: -3.0874

Max Act: 2.0160. Min Act: -0.0001

Data Index: 356662 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.6573. Min Act: -0.0001

Data Index: 388881 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.6736. Min Act: -0.0001

Data Index: 1478946 (Python Code)

Max Activating Token Index: 216

Text #6

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.7980. Min Act: -0.0001

Data Index: 768 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.6646. Min Act: -0.0001

Data Index: 128570 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.7171. Min Act: -0.0001

Data Index: 1448878 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.7172. Min Act: -0.0001

Data Index: 797078 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.5950. Min Act: -0.0001

Data Index: 936161 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.6684. Min Act: -0.0001

Data Index: 125491 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.5149. Min Act: -0.0001

Data Index: 1505276 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.6538. Min Act: -0.0001

Data Index: 1414250 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.5637. Min Act: -0.0001

Data Index: 1099860 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.8928. Min Act: -0.0001

Data Index: 950924 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.6736. Min Act: -0.0001

Data Index: 1196522 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.6902. Min Act: -0.0001

Data Index: 3965 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.3613. Min Act: -0.0001

Data Index: 937312 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.0874. Min Range: -3.0874

Max Act: 1.5976. Min Act: -0.0001

Data Index: 998929 (C4 (Web Text))

Max Activating Token Index: 342