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

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

Neuron 6106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0920. Min Range: -3.0920

Max Act: 3.0920. Min Act: -0.0000

Data Index: 157387 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.8212. Min Act: -0.0000

Data Index: 1045975 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.6899. Min Act: -0.0000

Data Index: 1084665 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.5220. Min Act: -0.0000

Data Index: 1096120 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.6361. Min Act: -0.0000

Data Index: 1001210 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.6452. Min Act: -0.0000

Data Index: 588043 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.7546. Min Act: -0.0000

Data Index: 196552 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.6991. Min Act: -0.0000

Data Index: 1262757 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.5692. Min Act: -0.0000

Data Index: 985994 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.5473. Min Act: -0.0000

Data Index: 1348230 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.3920. Min Act: -0.0000

Data Index: 889225 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.5071. Min Act: -0.0000

Data Index: 1084870 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.4952. Min Act: -0.0000

Data Index: 119672 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.4619. Min Act: -0.0000

Data Index: 662922 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.3408. Min Act: -0.0000

Data Index: 140721 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.4559. Min Act: -0.0000

Data Index: 1340337 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.5121. Min Act: -0.0000

Data Index: 240483 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.4011. Min Act: -0.0000

Data Index: 1221688 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.4737. Min Act: -0.0000

Data Index: 237495 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 3.0920. Min Range: -3.0920

Max Act: 2.3373. Min Act: -0.0000

Data Index: 1185172 (C4 (Web Text))

Max Activating Token Index: 106