Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3478 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.7303. Min Act: -0.0000

Data Index: 1478217 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.5742. Min Act: -0.0000

Data Index: 1423816 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.1936. Min Act: 0.0000

Data Index: 1557688 (Python Code)

Max Activating Token Index: 138

Text #3

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.4296. Min Act: -0.0000

Data Index: 1600902 (Python Code)

Max Activating Token Index: 1000

Text #4

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.2944. Min Act: -0.0000

Data Index: 1454669 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.2393. Min Act: -0.0000

Data Index: 1482524 (Python Code)

Max Activating Token Index: 927

Text #6

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.2368. Min Act: -0.0000

Data Index: 1409131 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.5033. Min Act: -0.0000

Data Index: 1495568 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.3280. Min Act: -0.0000

Data Index: 1382163 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.4265. Min Act: -0.0000

Data Index: 1547020 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.5269. Min Act: -0.0000

Data Index: 1471902 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.1554. Min Act: -0.0000

Data Index: 1455908 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.2994. Min Act: -0.0000

Data Index: 1545899 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 2.7303. Min Range: -2.7303

Max Act: 1.9321. Min Act: -0.0000

Data Index: 1374965 (Python Code)

Max Activating Token Index: 241

Text #14

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.0478. Min Act: -0.0000

Data Index: 1496407 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.2339. Min Act: -0.0000

Data Index: 1477600 (Python Code)

Max Activating Token Index: 712

Text #16

Max Range: 2.7303. Min Range: -2.7303

Max Act: 1.9485. Min Act: -0.0000

Data Index: 1613842 (Python Code)

Max Activating Token Index: 591

Text #17

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.0179. Min Act: -0.0000

Data Index: 1483185 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.2331. Min Act: -0.0000

Data Index: 1453884 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 2.7303. Min Range: -2.7303

Max Act: 2.1006. Min Act: -0.0000

Data Index: 1422187 (Python Code)

Max Activating Token Index: 1021