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

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

Neuron 2407 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3929. Min Range: -3.3929

Max Act: 3.2748. Min Act: -0.0002

Data Index: 365423 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.9778. Min Act: -0.0002

Data Index: 238758 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 3.3929. Min Range: -3.3929

Max Act: 3.3929. Min Act: -0.0001

Data Index: 701633 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.9154. Min Act: -0.0001

Data Index: 244338 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 3.3929. Min Range: -3.3929

Max Act: 3.1703. Min Act: -0.0001

Data Index: 969114 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 3.3929. Min Range: -3.3929

Max Act: 3.0591. Min Act: -0.0002

Data Index: 1186030 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.9235. Min Act: -0.0002

Data Index: 1158104 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.7291. Min Act: -0.0001

Data Index: 893359 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.9555. Min Act: -0.0002

Data Index: 345942 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 3.3929. Min Range: -3.3929

Max Act: 3.0669. Min Act: -0.0002

Data Index: 858244 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.6588. Min Act: -0.0002

Data Index: 2970 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.7620. Min Act: -0.0002

Data Index: 1010438 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.7262. Min Act: -0.0002

Data Index: 60001 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.9785. Min Act: -0.0001

Data Index: 936719 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.6846. Min Act: -0.0001

Data Index: 1176869 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.4395. Min Act: -0.0001

Data Index: 784785 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.5045. Min Act: -0.0001

Data Index: 927236 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.5526. Min Act: -0.0001

Data Index: 340676 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.4040. Min Act: -0.0001

Data Index: 20674 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 3.3929. Min Range: -3.3929

Max Act: 2.5415. Min Act: -0.0001

Data Index: 677539 (C4 (Web Text))

Max Activating Token Index: 214