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

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

Neuron 1823 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: 1.2491. Min Range: -1.2491

Max Act: 1.1726. Min Act: -0.0000

Data Index: 939282 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1321025 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1965. Min Act: -0.0000

Data Index: 242946 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1753. Min Act: -0.0000

Data Index: 799198 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0852. Min Act: -0.0000

Data Index: 297562 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1763. Min Act: -0.0000

Data Index: 874115 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.2071. Min Act: -0.0000

Data Index: 789333 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1109392 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1967. Min Act: -0.0000

Data Index: 272435 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1451. Min Act: -0.0000

Data Index: 325986 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.2175. Min Act: -0.0000

Data Index: 1177115 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1023714 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1272670 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0502. Min Act: -0.0000

Data Index: 453786 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0798. Min Act: -0.0000

Data Index: 373738 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0805. Min Act: -0.0000

Data Index: 171988 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0719. Min Act: -0.0000

Data Index: 681960 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.0694. Min Act: -0.0000

Data Index: 527713 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1388. Min Act: -0.0000

Data Index: 940707 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.2491. Min Range: -1.2491

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1082604 (C4 (Web Text))

Max Activating Token Index: 63