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

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

Neuron 2773 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1587590 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.7393. Min Act: 0.0001

Data Index: 1529691 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6740. Min Act: -0.0001

Data Index: 1413285 (Python Code)

Max Activating Token Index: 846

Text #3

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1585587 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1531697 (Python Code)

Max Activating Token Index: 573

Text #5

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6627. Min Act: 0.0000

Data Index: 1450161 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1485766 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1474174 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1584621 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6138. Min Act: 0.0001

Data Index: 1645855 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1461237 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6248. Min Act: 0.0001

Data Index: 1494520 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1598238 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5754. Min Act: -0.0001

Data Index: 1368689 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5929. Min Act: -0.0001

Data Index: 1393730 (Python Code)

Max Activating Token Index: 271

Text #15

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.6063. Min Act: -0.0001

Data Index: 1379964 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1592581 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1483044 (Python Code)

Max Activating Token Index: 491

Text #18

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1387211 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 0.7572. Min Range: -0.7572

Max Act: 0.5672. Min Act: 0.0000

Data Index: 1557027 (Python Code)

Max Activating Token Index: 984