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

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

Neuron 3382 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2601. Min Act: -0.0002

Data Index: 308542 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2099. Min Act: -0.0002

Data Index: 838320 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1909. Min Act: -0.0002

Data Index: 984394 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2043. Min Act: -0.0002

Data Index: 1253787 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1726. Min Act: -0.0002

Data Index: 888134 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1632. Min Act: -0.0001

Data Index: 453374 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1668. Min Act: -0.0002

Data Index: 990531 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1034103 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1700. Min Act: -0.0002

Data Index: 1320237 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1625. Min Act: -0.0002

Data Index: 914166 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1614. Min Act: -0.0002

Data Index: 678007 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1718. Min Act: -0.0002

Data Index: 608262 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1570. Min Act: -0.0002

Data Index: 765509 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1690. Min Act: -0.0001

Data Index: 803728 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1620. Min Act: -0.0001

Data Index: 49177 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1522. Min Act: -0.0002

Data Index: 612388 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1570. Min Act: -0.0002

Data Index: 784948 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1501. Min Act: -0.0002

Data Index: 233640 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1438. Min Act: -0.0001

Data Index: 373240 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1455. Min Act: -0.0002

Data Index: 931865 (C4 (Web Text))

Max Activating Token Index: 727