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

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

Neuron 5796 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0607. Min Act: -0.0002

Data Index: 589761 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1083105 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0541. Min Act: -0.0002

Data Index: 555924 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0507. Min Act: -0.0002

Data Index: 591884 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1654175 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0462. Min Act: -0.0002

Data Index: 270082 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1232117 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1570371 (Python Code)

Max Activating Token Index: 519

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0441. Min Act: -0.0002

Data Index: 524408 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0002

Data Index: 616950 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1522215 (Python Code)

Max Activating Token Index: 441

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0418. Min Act: -0.0002

Data Index: 88834 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0449. Min Act: -0.0002

Data Index: 489908 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0418. Min Act: -0.0002

Data Index: 146020 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0440. Min Act: -0.0002

Data Index: 902446 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0383. Min Act: -0.0002

Data Index: 497469 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1299761 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1239513 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0402. Min Act: -0.0002

Data Index: 762678 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1165526 (C4 (Web Text))

Max Activating Token Index: 560