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

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

Neuron 4044 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.7405. Min Act: -0.0000

Data Index: 1614398 (Python Code)

Max Activating Token Index: 953

Text #1

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.6311. Min Act: -0.0000

Data Index: 1470367 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.6503. Min Act: -0.0000

Data Index: 1585262 (Python Code)

Max Activating Token Index: 138

Text #3

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1541732 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1336479 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1597204 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.5785. Min Act: -0.0000

Data Index: 711787 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1637120 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.4893. Min Act: -0.0000

Data Index: 1364380 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.6612. Min Act: -0.0000

Data Index: 1483276 (Python Code)

Max Activating Token Index: 895

Text #10

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.5230. Min Act: -0.0000

Data Index: 1399135 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1495750 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1562851 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.4611. Min Act: -0.0000

Data Index: 260610 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.6189. Min Act: -0.0000

Data Index: 821784 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.6536. Min Act: -0.0000

Data Index: 423972 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1146624 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.5623. Min Act: -0.0000

Data Index: 1486472 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1634516 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 1.7405. Min Range: -1.7405

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1607218 (Python Code)

Max Activating Token Index: 472