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

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

Neuron 1431 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.7407. Min Act: -0.0000

Data Index: 198848 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.7073. Min Act: -0.0001

Data Index: 1459861 (Python Code)

Max Activating Token Index: 605

Text #2

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6641. Min Act: -0.0001

Data Index: 320937 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5230. Min Act: -0.0001

Data Index: 1465709 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6819. Min Act: -0.0000

Data Index: 905915 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.7467. Min Act: -0.0001

Data Index: 1608106 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6725. Min Act: -0.0001

Data Index: 1355096 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6466. Min Act: -0.0000

Data Index: 157252 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6718. Min Act: -0.0001

Data Index: 334643 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6409. Min Act: -0.0001

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6669. Min Act: -0.0000

Data Index: 269859 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6387. Min Act: -0.0001

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6247. Min Act: -0.0001

Data Index: 198916 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5877. Min Act: -0.0000

Data Index: 948510 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5975. Min Act: -0.0001

Data Index: 1561681 (Python Code)

Max Activating Token Index: 481

Text #15

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6374. Min Act: -0.0001

Data Index: 523684 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6040. Min Act: -0.0001

Data Index: 1237167 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6022. Min Act: -0.0000

Data Index: 212307 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5950. Min Act: -0.0000

Data Index: 224683 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6076. Min Act: -0.0001

Data Index: 998440 (C4 (Web Text))

Max Activating Token Index: 466