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

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

Neuron 3533 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: 0.0838. Min Range: -0.0838

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1611955 (Python Code)

Max Activating Token Index: 763

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0002

Data Index: 58493 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0754. Min Act: -0.0001

Data Index: 57906 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0765. Min Act: -0.0001

Data Index: 545742 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1651443 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0658. Min Act: -0.0002

Data Index: 955959 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1435592 (Python Code)

Max Activating Token Index: 516

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0637. Min Act: -0.0002

Data Index: 576989 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1234561 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1254222 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0671. Min Act: -0.0002

Data Index: 972342 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0697. Min Act: -0.0001

Data Index: 557795 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1513359 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0708. Min Act: -0.0002

Data Index: 724396 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1034391 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1457351 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0663. Min Act: -0.0002

Data Index: 776174 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0640. Min Act: -0.0002

Data Index: 178452 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1150755 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1292120 (C4 (Web Text))

Max Activating Token Index: 991