Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2416 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0000

Data Index: 96638 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0610. Min Act: -0.0000

Data Index: 234064 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0508. Min Act: -0.0000

Data Index: 219418 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1403037 (Python Code)

Max Activating Token Index: 479

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0415. Min Act: -0.0000

Data Index: 577898 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0530. Min Act: -0.0000

Data Index: 223281 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0500. Min Act: -0.0000

Data Index: 859434 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0482. Min Act: -0.0000

Data Index: 212079 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0503. Min Act: -0.0000

Data Index: 405991 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0481. Min Act: -0.0000

Data Index: 448866 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0450. Min Act: -0.0000

Data Index: 1430041 (Python Code)

Max Activating Token Index: 287

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0491. Min Act: -0.0000

Data Index: 764353 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1290662 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0365. Min Act: -0.0000

Data Index: 752283 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1004936 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0427. Min Act: -0.0000

Data Index: 585122 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0459. Min Act: -0.0000

Data Index: 493077 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1020033 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0481. Min Act: -0.0000

Data Index: 84956 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0440. Min Act: -0.0000

Data Index: 224387 (C4 (Web Text))

Max Activating Token Index: 794