Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1210 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0003

Data Index: 118609 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1115100 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0682. Min Act: -0.0002

Data Index: 636139 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0644. Min Act: -0.0003

Data Index: 871577 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0637. Min Act: -0.0004

Data Index: 838606 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0646. Min Act: -0.0002

Data Index: 775811 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0620. Min Act: -0.0003

Data Index: 675280 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0624. Min Act: -0.0002

Data Index: 272385 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0608. Min Act: -0.0003

Data Index: 687472 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0621. Min Act: -0.0003

Data Index: 25845 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0606. Min Act: -0.0003

Data Index: 15368 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1220102 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0611. Min Act: -0.0003

Data Index: 149980 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0605. Min Act: -0.0002

Data Index: 556303 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0603. Min Act: -0.0003

Data Index: 685038 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1120251 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0591. Min Act: -0.0003

Data Index: 161532 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1056893 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0599. Min Act: -0.0003

Data Index: 390769 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0588. Min Act: -0.0003

Data Index: 179267 (C4 (Web Text))

Max Activating Token Index: 606