Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 786 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0003

Data Index: 189160 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0768. Min Act: -0.0004

Data Index: 330675 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1344972 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1236661 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0776. Min Act: -0.0002

Data Index: 445551 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1266745 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0730. Min Act: -0.0003

Data Index: 392324 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0728. Min Act: -0.0003

Data Index: 43316 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0720. Min Act: -0.0003

Data Index: 266145 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0729. Min Act: -0.0004

Data Index: 415172 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1004622 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0685. Min Act: -0.0003

Data Index: 911980 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0753. Min Act: -0.0004

Data Index: 1183991 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0724. Min Act: -0.0003

Data Index: 406347 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0702. Min Act: -0.0003

Data Index: 571481 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0690. Min Act: -0.0003

Data Index: 903466 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0724. Min Act: -0.0003

Data Index: 528095 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0714. Min Act: -0.0003

Data Index: 279826 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0707. Min Act: -0.0003

Data Index: 82469 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0703. Min Act: -0.0003

Data Index: 912434 (C4 (Web Text))

Max Activating Token Index: 366