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

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

Neuron 3461 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: 1.3776. Min Range: -1.3776

Max Act: 1.3625. Min Act: -0.0000

Data Index: 54240 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.3776. Min Act: -0.0000

Data Index: 466291 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1224965 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0803. Min Act: -0.0000

Data Index: 560985 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.1097. Min Act: -0.0000

Data Index: 973602 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0638. Min Act: -0.0000

Data Index: 961890 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1284925 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.1070. Min Act: -0.0000

Data Index: 90118 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0614. Min Act: -0.0000

Data Index: 931534 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0830. Min Act: -0.0000

Data Index: 683195 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0433. Min Act: -0.0000

Data Index: 151183 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9592. Min Act: -0.0000

Data Index: 747983 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0302. Min Act: -0.0000

Data Index: 378410 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9552. Min Act: -0.0000

Data Index: 609405 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9668. Min Act: -0.0000

Data Index: 695979 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9885. Min Act: -0.0000

Data Index: 97353 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0141. Min Act: -0.0000

Data Index: 102410 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9407. Min Act: -0.0000

Data Index: 955739 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9519. Min Act: -0.0000

Data Index: 299563 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1103122 (C4 (Web Text))

Max Activating Token Index: 344