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

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

Neuron 1709 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: 0.8695. Min Range: -0.8695

Max Act: 0.8695. Min Act: -0.0002

Data Index: 630503 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7420. Min Act: -0.0001

Data Index: 920514 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1327505 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7020. Min Act: -0.0001

Data Index: 138982 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7719. Min Act: -0.0002

Data Index: 1290421 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7701. Min Act: -0.0001

Data Index: 794869 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7748. Min Act: -0.0002

Data Index: 405689 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7357. Min Act: -0.0002

Data Index: 184100 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7025. Min Act: -0.0001

Data Index: 676592 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7163. Min Act: -0.0002

Data Index: 660122 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7011. Min Act: -0.0001

Data Index: 950230 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.6502. Min Act: -0.0002

Data Index: 710649 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7626. Min Act: -0.0001

Data Index: 513093 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7340. Min Act: -0.0002

Data Index: 869250 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7892. Min Act: -0.0002

Data Index: 227845 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.7607. Min Act: -0.0001

Data Index: 364679 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.6670. Min Act: -0.0002

Data Index: 1159611 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.6002. Min Act: -0.0001

Data Index: 157581 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.6605. Min Act: -0.0002

Data Index: 1325542 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.8695. Min Range: -0.8695

Max Act: 0.6845. Min Act: -0.0002

Data Index: 811090 (C4 (Web Text))

Max Activating Token Index: 33