Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2501 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1527043 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0723. Min Act: -0.0001

Data Index: 428928 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1142337 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1443140 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1533233 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0624. Min Act: -0.0001

Data Index: 328030 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1582032 (Python Code)

Max Activating Token Index: 860

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0528. Min Act: -0.0001

Data Index: 235187 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1604724 (Python Code)

Max Activating Token Index: 765

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1616522 (Python Code)

Max Activating Token Index: 401

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1413321 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1524123 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0576. Min Act: -0.0001

Data Index: 859946 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1599965 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1495316 (Python Code)

Max Activating Token Index: 311

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1563620 (Python Code)

Max Activating Token Index: 847

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1433833 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1426455 (Python Code)

Max Activating Token Index: 699

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1378570 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1608716 (Python Code)

Max Activating Token Index: 967