Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1767 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.7725. Min Act: -0.0001

Data Index: 146573 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.1911. Min Act: -0.0001

Data Index: 539158 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.9055. Min Act: -0.0001

Data Index: 1080977 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.7559. Min Act: -0.0000

Data Index: 641650 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.4909. Min Act: -0.0001

Data Index: 77188 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.1997. Min Act: -0.0000

Data Index: 1325567 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.2400. Min Act: -0.0001

Data Index: 608115 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.4037. Min Act: -0.0001

Data Index: 1175368 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.1915. Min Act: -0.0001

Data Index: 1265472 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.1092. Min Act: -0.0001

Data Index: 508553 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.0485. Min Act: -0.0001

Data Index: 180216 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 5.7725. Min Range: -5.7725

Max Act: 3.8624. Min Act: -0.0001

Data Index: 1308115 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.0038. Min Act: -0.0001

Data Index: 256508 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.0060. Min Act: -0.0001

Data Index: 714520 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.0246. Min Act: -0.0000

Data Index: 1103520 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 5.7725. Min Range: -5.7725

Max Act: 3.9586. Min Act: -0.0001

Data Index: 184495 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 5.7725. Min Range: -5.7725

Max Act: 3.9621. Min Act: -0.0001

Data Index: 819338 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 5.7725. Min Range: -5.7725

Max Act: 4.0577. Min Act: -0.0001

Data Index: 755584 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 5.7725. Min Range: -5.7725

Max Act: 3.8730. Min Act: -0.0001

Data Index: 479233 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 5.7725. Min Range: -5.7725

Max Act: 3.9770. Min Act: -0.0001

Data Index: 758071 (C4 (Web Text))

Max Activating Token Index: 378