Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1867 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.5031. Min Act: -0.0000

Data Index: 573542 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1062639 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0448. Min Act: -0.0000

Data Index: 540784 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.5031. Min Range: -1.5031

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1317483 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9571. Min Act: -0.0000

Data Index: 263938 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9826. Min Act: -0.0000

Data Index: 789784 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9221. Min Act: -0.0000

Data Index: 313289 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9282. Min Act: -0.0000

Data Index: 614004 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9723. Min Act: -0.0000

Data Index: 681084 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9472. Min Act: -0.0000

Data Index: 649193 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9316. Min Act: -0.0000

Data Index: 941607 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.8930. Min Act: -0.0000

Data Index: 74888 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.9310. Min Act: -0.0000

Data Index: 512915 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.8184. Min Act: -0.0000

Data Index: 46495 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.8433. Min Act: -0.0000

Data Index: 153120 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.8006. Min Act: -0.0000

Data Index: 190662 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1132634 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.8147. Min Act: -0.0000

Data Index: 853172 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.7372. Min Act: -0.0000

Data Index: 560377 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.5031. Min Range: -1.5031

Max Act: 0.7567. Min Act: 0.0000

Data Index: 4694 (C4 (Web Text))

Max Activating Token Index: 967