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

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

Neuron 5888 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: 3.5968. Min Range: -3.5968

Max Act: 3.3875. Min Act: -0.0000

Data Index: 1534288 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.4332. Min Act: -0.0000

Data Index: 1625452 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.5968. Min Act: -0.0000

Data Index: 1615530 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0387. Min Act: -0.0000

Data Index: 1655066 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0434. Min Act: -0.0000

Data Index: 1540893 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0400. Min Act: -0.0000

Data Index: 1397709 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.1465. Min Act: -0.0000

Data Index: 1420151 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0517. Min Act: -0.0000

Data Index: 1365321 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0306. Min Act: -0.0000

Data Index: 1444497 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8393. Min Act: -0.0000

Data Index: 1404040 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1388756 (Python Code)

Max Activating Token Index: 406

Text #11

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8865. Min Act: -0.0000

Data Index: 1523107 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8406. Min Act: -0.0000

Data Index: 1383221 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8277. Min Act: -0.0000

Data Index: 1615929 (Python Code)

Max Activating Token Index: 449

Text #14

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.0663. Min Act: -0.0000

Data Index: 1523709 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 3.5968. Min Range: -3.5968

Max Act: 3.2225. Min Act: -0.0000

Data Index: 1504067 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.7883. Min Act: -0.0000

Data Index: 1633580 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8610. Min Act: -0.0000

Data Index: 1642869 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.8430. Min Act: -0.0000

Data Index: 1648422 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 3.5968. Min Range: -3.5968

Max Act: 2.5644. Min Act: -0.0000

Data Index: 1472912 (Python Code)

Max Activating Token Index: 356