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

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

Neuron 4841 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.6216. Min Act: -0.0000

Data Index: 1588631 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.5444. Min Act: -0.0000

Data Index: 1444832 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.2559. Min Act: -0.0000

Data Index: 1387381 (Python Code)

Max Activating Token Index: 341

Text #3

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.4118. Min Act: -0.0001

Data Index: 1624686 (Python Code)

Max Activating Token Index: 910

Text #4

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.4056. Min Act: -0.0000

Data Index: 1474282 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.1078. Min Act: -0.0000

Data Index: 1410557 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.1000. Min Act: -0.0000

Data Index: 1559692 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.0370. Min Act: -0.0000

Data Index: 1578073 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.0182. Min Act: -0.0001

Data Index: 1424852 (Python Code)

Max Activating Token Index: 438

Text #9

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1437370 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 2.6216. Min Range: -2.6216

Max Act: 1.9257. Min Act: -0.0000

Data Index: 1584492 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.0267. Min Act: -0.0000

Data Index: 1394197 (Python Code)

Max Activating Token Index: 452

Text #12

Max Range: 2.6216. Min Range: -2.6216

Max Act: 1.9915. Min Act: -0.0000

Data Index: 1439080 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.0935. Min Act: -0.0000

Data Index: 1593930 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 2.6216. Min Range: -2.6216

Max Act: 1.9669. Min Act: -0.0000

Data Index: 1650997 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 2.6216. Min Range: -2.6216

Max Act: 1.8481. Min Act: -0.0000

Data Index: 1505776 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 2.6216. Min Range: -2.6216

Max Act: 1.9090. Min Act: -0.0000

Data Index: 1485671 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 2.6216. Min Range: -2.6216

Max Act: 1.9041. Min Act: -0.0000

Data Index: 1449740 (Python Code)

Max Activating Token Index: 780

Text #18

Max Range: 2.6216. Min Range: -2.6216

Max Act: 1.8960. Min Act: -0.0000

Data Index: 1498628 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 2.6216. Min Range: -2.6216

Max Act: 2.2336. Min Act: -0.0000

Data Index: 1640386 (Python Code)

Max Activating Token Index: 910