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

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

Neuron 3758 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.8040. Min Act: -0.0000

Data Index: 1412078 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.9465. Min Act: -0.0000

Data Index: 1466702 (Python Code)

Max Activating Token Index: 590

Text #2

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.5537. Min Act: -0.0000

Data Index: 1458985 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.4429. Min Act: -0.0000

Data Index: 1487288 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.4629. Min Act: -0.0000

Data Index: 1586711 (Python Code)

Max Activating Token Index: 1004

Text #5

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.4601. Min Act: -0.0000

Data Index: 1443594 (Python Code)

Max Activating Token Index: 704

Text #6

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.3227. Min Act: -0.0000

Data Index: 1511703 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.3591. Min Act: -0.0000

Data Index: 1379425 (Python Code)

Max Activating Token Index: 588

Text #8

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.6899. Min Act: -0.0000

Data Index: 1558194 (Python Code)

Max Activating Token Index: 912

Text #9

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.1092. Min Act: -0.0000

Data Index: 1437753 (Python Code)

Max Activating Token Index: 940

Text #10

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.4747. Min Act: -0.0000

Data Index: 1507028 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.4406. Min Act: -0.0000

Data Index: 1464356 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.4557. Min Act: -0.0000

Data Index: 1598649 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.2283. Min Act: -0.0000

Data Index: 1655723 (Python Code)

Max Activating Token Index: 480

Text #14

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.0221. Min Act: -0.0000

Data Index: 1503714 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.2116. Min Act: -0.0000

Data Index: 1471543 (Python Code)

Max Activating Token Index: 762

Text #16

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.2919. Min Act: -0.0000

Data Index: 1555634 (Python Code)

Max Activating Token Index: 961

Text #17

Max Range: 5.9465. Min Range: -5.9465

Max Act: 4.9032. Min Act: -0.0000

Data Index: 1510499 (Python Code)

Max Activating Token Index: 724

Text #18

Max Range: 5.9465. Min Range: -5.9465

Max Act: 5.2919. Min Act: -0.0000

Data Index: 1561336 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 5.9465. Min Range: -5.9465

Max Act: 4.8909. Min Act: -0.0000

Data Index: 1653937 (Python Code)

Max Activating Token Index: 947