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

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

Neuron 1220 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.5028. Min Range: -5.5028

Max Act: 5.5028. Min Act: -0.0001

Data Index: 1488643 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 5.5028. Min Range: -5.5028

Max Act: 5.4569. Min Act: -0.0001

Data Index: 1425785 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.8487. Min Act: -0.0001

Data Index: 1396618 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.9756. Min Act: -0.0001

Data Index: 1360262 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.9061. Min Act: -0.0001

Data Index: 1650698 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.8077. Min Act: -0.0001

Data Index: 1621149 (Python Code)

Max Activating Token Index: 893

Text #6

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.7241. Min Act: -0.0001

Data Index: 1655701 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.3450. Min Act: -0.0001

Data Index: 1646295 (Python Code)

Max Activating Token Index: 709

Text #8

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.6382. Min Act: -0.0001

Data Index: 1618472 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.4766. Min Act: -0.0001

Data Index: 1570103 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.7399. Min Act: -0.0001

Data Index: 1646107 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.5563. Min Act: -0.0001

Data Index: 1564699 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.5622. Min Act: -0.0001

Data Index: 1442279 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.3754. Min Act: -0.0001

Data Index: 1587208 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.3616. Min Act: -0.0001

Data Index: 1465726 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.7291. Min Act: -0.0001

Data Index: 1386363 (Python Code)

Max Activating Token Index: 776

Text #16

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.7178. Min Act: -0.0001

Data Index: 1503792 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.2507. Min Act: -0.0001

Data Index: 1593947 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.5366. Min Act: -0.0001

Data Index: 1488227 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 5.5028. Min Range: -5.5028

Max Act: 3.3406. Min Act: -0.0001

Data Index: 1611831 (Python Code)

Max Activating Token Index: 606