Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1964 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6670. Min Range: -2.6670

Max Act: 2.3849. Min Act: -0.0000

Data Index: 1436104 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 2.6670. Min Range: -2.6670

Max Act: 2.4955. Min Act: -0.0000

Data Index: 1462219 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 2.6670. Min Range: -2.6670

Max Act: 2.6670. Min Act: -0.0000

Data Index: 1459438 (Python Code)

Max Activating Token Index: 595

Text #3

Max Range: 2.6670. Min Range: -2.6670

Max Act: 2.4946. Min Act: -0.0000

Data Index: 1655188 (Python Code)

Max Activating Token Index: 108

Text #4

Max Range: 2.6670. Min Range: -2.6670

Max Act: 2.6651. Min Act: -0.0000

Data Index: 1522813 (Python Code)

Max Activating Token Index: 453

Text #5

Max Range: 2.6670. Min Range: -2.6670

Max Act: 2.1761. Min Act: -0.0000

Data Index: 764874 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.9905. Min Act: -0.0000

Data Index: 1409178 (Python Code)

Max Activating Token Index: 1019

Text #7

Max Range: 2.6670. Min Range: -2.6670

Max Act: 2.3091. Min Act: -0.0000

Data Index: 1365556 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.9768. Min Act: -0.0000

Data Index: 799054 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.9766. Min Act: -0.0000

Data Index: 1082093 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.8007. Min Act: -0.0000

Data Index: 62256 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.7684. Min Act: -0.0000

Data Index: 888019 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.7487. Min Act: -0.0000

Data Index: 414827 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.8343. Min Act: -0.0000

Data Index: 150489 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1505954 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.5893. Min Act: -0.0000

Data Index: 545557 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.5515. Min Act: -0.0000

Data Index: 1029457 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.7657. Min Act: -0.0000

Data Index: 244805 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.7167. Min Act: -0.0000

Data Index: 350170 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 2.6670. Min Range: -2.6670

Max Act: 1.4627. Min Act: -0.0000

Data Index: 132545 (C4 (Web Text))

Max Activating Token Index: 489