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

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

Neuron 2044 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3863. Min Range: -4.3863

Max Act: 4.3348. Min Act: -0.0000

Data Index: 753794 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 4.3863. Min Range: -4.3863

Max Act: 4.2536. Min Act: -0.0001

Data Index: 636146 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 4.3863. Min Range: -4.3863

Max Act: 4.3863. Min Act: -0.0001

Data Index: 710586 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 4.3863. Min Range: -4.3863

Max Act: 4.0006. Min Act: -0.0000

Data Index: 1302738 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.8931. Min Act: -0.0000

Data Index: 1232415 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 4.3863. Min Range: -4.3863

Max Act: 4.0505. Min Act: -0.0000

Data Index: 683760 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.9878. Min Act: -0.0001

Data Index: 556474 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.6169. Min Act: -0.0000

Data Index: 584667 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.7484. Min Act: -0.0001

Data Index: 560752 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.6585. Min Act: -0.0000

Data Index: 852167 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.3417. Min Act: -0.0001

Data Index: 1228125 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.5050. Min Act: -0.0000

Data Index: 817923 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.3056. Min Act: -0.0000

Data Index: 1274390 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.3829. Min Act: -0.0001

Data Index: 90309 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.2232. Min Act: -0.0001

Data Index: 706577 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.3562. Min Act: -0.0000

Data Index: 534702 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.4877. Min Act: -0.0000

Data Index: 354733 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.4787. Min Act: -0.0001

Data Index: 1186365 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.4472. Min Act: -0.0001

Data Index: 846735 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 4.3863. Min Range: -4.3863

Max Act: 3.2844. Min Act: -0.0000

Data Index: 616535 (C4 (Web Text))

Max Activating Token Index: 53