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

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

Neuron 4107 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.0080. Min Range: -9.0080

Max Act: 9.0080. Min Act: -0.0000

Data Index: 1564733 (Python Code)

Max Activating Token Index: 807

Text #1

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.8306. Min Act: -0.0000

Data Index: 1489397 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.9385. Min Act: -0.0000

Data Index: 1368066 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.8967. Min Act: -0.0000

Data Index: 1464315 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.8930. Min Act: -0.0000

Data Index: 1632262 (Python Code)

Max Activating Token Index: 417

Text #5

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.8827. Min Act: -0.0000

Data Index: 1639357 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.8861. Min Act: -0.0000

Data Index: 1630278 (Python Code)

Max Activating Token Index: 796

Text #7

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.8758. Min Act: -0.0000

Data Index: 1575789 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.8462. Min Act: -0.0000

Data Index: 1581636 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.9406. Min Act: -0.0000

Data Index: 1637527 (Python Code)

Max Activating Token Index: 875

Text #10

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.7758. Min Act: -0.0000

Data Index: 1592322 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.7256. Min Act: -0.0000

Data Index: 1409655 (Python Code)

Max Activating Token Index: 378

Text #12

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.7304. Min Act: -0.0000

Data Index: 1511861 (Python Code)

Max Activating Token Index: 896

Text #13

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.5447. Min Act: -0.0000

Data Index: 1612355 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.4222. Min Act: -0.0000

Data Index: 1410548 (Python Code)

Max Activating Token Index: 872

Text #15

Max Range: 9.0080. Min Range: -9.0080

Max Act: 8.1914. Min Act: -0.0000

Data Index: 1551723 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 9.0080. Min Range: -9.0080

Max Act: 7.8997. Min Act: -0.0000

Data Index: 1567971 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 9.0080. Min Range: -9.0080

Max Act: 7.6893. Min Act: -0.0000

Data Index: 1548848 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 9.0080. Min Range: -9.0080

Max Act: 7.9980. Min Act: -0.0000

Data Index: 1518556 (Python Code)

Max Activating Token Index: 554

Text #19

Max Range: 9.0080. Min Range: -9.0080

Max Act: 7.6252. Min Act: -0.0000

Data Index: 1366409 (Python Code)

Max Activating Token Index: 521