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

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

Neuron 3901 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: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1637714 (Python Code)

Max Activating Token Index: 522

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1583414 (Python Code)

Max Activating Token Index: 600

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1586071 (Python Code)

Max Activating Token Index: 940

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1364405 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1523949 (Python Code)

Max Activating Token Index: 839

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1487840 (Python Code)

Max Activating Token Index: 427

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1558495 (Python Code)

Max Activating Token Index: 790

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1447910 (Python Code)

Max Activating Token Index: 481

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1650021 (Python Code)

Max Activating Token Index: 852

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1482519 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1442565 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1611158 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1613102 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1481727 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1548931 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0634. Min Act: -0.0000

Data Index: 110128 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1631971 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1645387 (Python Code)

Max Activating Token Index: 143

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1562662 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1655782 (Python Code)

Max Activating Token Index: 612