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

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

Neuron 3038 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.5690. Min Act: -0.0001

Data Index: 1049472 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4621. Min Act: -0.0001

Data Index: 1107093 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4308. Min Act: -0.0001

Data Index: 537606 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4139. Min Act: -0.0001

Data Index: 889831 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3768. Min Act: -0.0001

Data Index: 312750 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.4049. Min Act: -0.0001

Data Index: 1288555 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3749. Min Act: -0.0001

Data Index: 957950 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3792. Min Act: -0.0001

Data Index: 890995 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3597. Min Act: -0.0001

Data Index: 165196 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3400. Min Act: -0.0001

Data Index: 242721 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3527. Min Act: -0.0001

Data Index: 416967 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3446. Min Act: -0.0001

Data Index: 87645 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1059218 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3309. Min Act: -0.0001

Data Index: 1252376 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3399. Min Act: -0.0001

Data Index: 874919 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3338. Min Act: -0.0001

Data Index: 760660 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1053505 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1118102 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1272916 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.5690. Min Range: -0.5690

Max Act: 0.3069. Min Act: -0.0001

Data Index: 1157 (C4 (Web Text))

Max Activating Token Index: 660