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

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

Neuron 1479 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3071. Min Range: -2.3071

Max Act: 2.3071. Min Act: -0.0000

Data Index: 1372954 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1466963 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1633167 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1501477 (Python Code)

Max Activating Token Index: 698

Text #4

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1555749 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1491304 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.4448. Min Act: -0.0000

Data Index: 1405597 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1644433 (Python Code)

Max Activating Token Index: 925

Text #8

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1409409 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.3647. Min Act: -0.0000

Data Index: 1596594 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1392432 (Python Code)

Max Activating Token Index: 297

Text #11

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1529096 (Python Code)

Max Activating Token Index: 236

Text #12

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1547353 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1371922 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.2094. Min Act: -0.0000

Data Index: 1407422 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.2692. Min Act: -0.0000

Data Index: 1467424 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1375704 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1388111 (Python Code)

Max Activating Token Index: 894

Text #18

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1644087 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 2.3071. Min Range: -2.3071

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1466221 (Python Code)

Max Activating Token Index: 108