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

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

Neuron 3974 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: 2.9089. Min Range: -2.9089

Max Act: 2.9089. Min Act: -0.0000

Data Index: 1554297 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.6409. Min Act: -0.0000

Data Index: 1419196 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.7454. Min Act: -0.0000

Data Index: 1364133 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.5101. Min Act: -0.0000

Data Index: 1641701 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.4582. Min Act: -0.0000

Data Index: 1626024 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3979. Min Act: -0.0000

Data Index: 1640897 (Python Code)

Max Activating Token Index: 594

Text #6

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3201. Min Act: -0.0000

Data Index: 1424756 (Python Code)

Max Activating Token Index: 335

Text #7

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2966. Min Act: -0.0000

Data Index: 1473157 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2720. Min Act: -0.0000

Data Index: 1607073 (Python Code)

Max Activating Token Index: 639

Text #9

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2349. Min Act: -0.0000

Data Index: 1522976 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1898. Min Act: -0.0000

Data Index: 1387623 (Python Code)

Max Activating Token Index: 947

Text #11

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2142. Min Act: -0.0000

Data Index: 1614215 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1819. Min Act: -0.0000

Data Index: 1514786 (Python Code)

Max Activating Token Index: 299

Text #13

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3036. Min Act: -0.0000

Data Index: 1405217 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1846. Min Act: -0.0000

Data Index: 1421792 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2301. Min Act: -0.0000

Data Index: 1550369 (Python Code)

Max Activating Token Index: 214

Text #16

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1339. Min Act: -0.0000

Data Index: 1655701 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1499867 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3444. Min Act: -0.0000

Data Index: 1469542 (Python Code)

Max Activating Token Index: 778

Text #19

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1579242 (Python Code)

Max Activating Token Index: 647