Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1680 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0002

Data Index: 928575 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1297295 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1189424 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0671. Min Act: -0.0002

Data Index: 687765 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0643. Min Act: -0.0002

Data Index: 361356 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1282262 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1284771 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0620. Min Act: -0.0002

Data Index: 976071 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0606. Min Act: -0.0001

Data Index: 810517 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1049666 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1204665 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0588. Min Act: -0.0002

Data Index: 137533 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0622. Min Act: -0.0002

Data Index: 709734 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0596. Min Act: -0.0002

Data Index: 343514 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0598. Min Act: -0.0001

Data Index: 184343 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0594. Min Act: -0.0002

Data Index: 206913 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0586. Min Act: -0.0002

Data Index: 803945 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0586. Min Act: -0.0001

Data Index: 234003 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0587. Min Act: -0.0002

Data Index: 141154 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0576. Min Act: -0.0002

Data Index: 877701 (C4 (Web Text))

Max Activating Token Index: 613