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

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

Neuron 959 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2700. Min Range: -3.2700

Max Act: 3.2534. Min Act: -0.0000

Data Index: 1642581 (Python Code)

Max Activating Token Index: 964

Text #1

Max Range: 3.2700. Min Range: -3.2700

Max Act: 3.2700. Min Act: -0.0000

Data Index: 1396401 (Python Code)

Max Activating Token Index: 240

Text #2

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.9545. Min Act: -0.0000

Data Index: 1621731 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.7558. Min Act: -0.0000

Data Index: 1537593 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.5886. Min Act: -0.0000

Data Index: 1646221 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.3268. Min Act: -0.0000

Data Index: 1648969 (Python Code)

Max Activating Token Index: 501

Text #6

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.3205. Min Act: -0.0000

Data Index: 1446994 (Python Code)

Max Activating Token Index: 988

Text #7

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.3871. Min Act: -0.0000

Data Index: 1426560 (Python Code)

Max Activating Token Index: 309

Text #8

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.3950. Min Act: -0.0000

Data Index: 1605296 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.1411. Min Act: -0.0000

Data Index: 1582237 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1432073 (Python Code)

Max Activating Token Index: 1013

Text #11

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.0736. Min Act: -0.0000

Data Index: 1601586 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 3.2700. Min Range: -3.2700

Max Act: 2.2846. Min Act: -0.0000

Data Index: 1556642 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 3.2700. Min Range: -3.2700

Max Act: 1.9619. Min Act: -0.0000

Data Index: 1495260 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 3.2700. Min Range: -3.2700

Max Act: 1.8321. Min Act: -0.0000

Data Index: 1439408 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 3.2700. Min Range: -3.2700

Max Act: 1.9257. Min Act: -0.0000

Data Index: 1493841 (Python Code)

Max Activating Token Index: 574

Text #16

Max Range: 3.2700. Min Range: -3.2700

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1434401 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 3.2700. Min Range: -3.2700

Max Act: 1.7993. Min Act: -0.0000

Data Index: 1433287 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 3.2700. Min Range: -3.2700

Max Act: 1.8045. Min Act: -0.0000

Data Index: 1496407 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 3.2700. Min Range: -3.2700

Max Act: 1.9923. Min Act: -0.0000

Data Index: 1651025 (Python Code)

Max Activating Token Index: 652