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

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

Neuron 1570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1562674 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1531797 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1431022 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1392693 (Python Code)

Max Activating Token Index: 513

Text #4

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1480804 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1604361 (Python Code)

Max Activating Token Index: 590

Text #6

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1504045 (Python Code)

Max Activating Token Index: 217

Text #7

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1644494 (Python Code)

Max Activating Token Index: 509

Text #8

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1378893 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1501548 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1571352 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1560326 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1449519 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1437814 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1459656 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1609680 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1523671 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1443770 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1586669 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1378724 (Python Code)

Max Activating Token Index: 198