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

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

Neuron 1583 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: 1.1838. Min Range: -1.1838

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1409308 (Python Code)

Max Activating Token Index: 78

Text #1

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1518491 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1382118 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7453. Min Act: 0.0000

Data Index: 1591125 (Python Code)

Max Activating Token Index: 103

Text #4

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1562432 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1487614 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6459. Min Act: 0.0000

Data Index: 1555208 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1380504 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6543. Min Act: 0.0000

Data Index: 1455166 (Python Code)

Max Activating Token Index: 479

Text #9

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1648310 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1496707 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1453317 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5136. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1586432 (Python Code)

Max Activating Token Index: 885

Text #14

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5538. Min Act: 0.0000

Data Index: 1621028 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.4650. Min Act: 0.0000

Data Index: 1593401 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.4954. Min Act: -0.0000

Data Index: 1498775 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5078. Min Act: 0.0000

Data Index: 1382885 (Python Code)

Max Activating Token Index: 507

Text #18

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5243. Min Act: 0.0000

Data Index: 1648669 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1431673 (Python Code)

Max Activating Token Index: 196