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

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

Neuron 5087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.9463. Min Act: -0.0000

Data Index: 557822 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.7427. Min Act: -0.0000

Data Index: 307403 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.4916. Min Act: -0.0000

Data Index: 969518 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.3651. Min Act: -0.0000

Data Index: 1058361 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.4738. Min Act: -0.0000

Data Index: 419677 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.3249. Min Act: -0.0000

Data Index: 426913 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.1929. Min Act: -0.0000

Data Index: 863729 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.2934. Min Act: -0.0000

Data Index: 355292 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.4038. Min Act: -0.0000

Data Index: 1298757 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.2726. Min Act: -0.0000

Data Index: 164861 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.1658. Min Act: -0.0000

Data Index: 188802 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.2705. Min Act: -0.0000

Data Index: 407601 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.3671. Min Act: -0.0000

Data Index: 1252375 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.1036. Min Act: -0.0000

Data Index: 970870 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.2341. Min Act: -0.0000

Data Index: 461552 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.2019. Min Act: -0.0000

Data Index: 838612 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.2047. Min Act: -0.0000

Data Index: 1173879 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.1638. Min Act: -0.0000

Data Index: 328571 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 2.9463. Min Range: -2.9463

Max Act: 1.9711. Min Act: -0.0000

Data Index: 258226 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 2.9463. Min Range: -2.9463

Max Act: 2.0677. Min Act: -0.0000

Data Index: 448440 (C4 (Web Text))

Max Activating Token Index: 856