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

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

Neuron 425 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: 1.6874. Min Range: -1.6874

Max Act: 1.6670. Min Act: -0.0000

Data Index: 1608792 (Python Code)

Max Activating Token Index: 944

Text #1

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5614. Min Act: -0.0001

Data Index: 1415977 (Python Code)

Max Activating Token Index: 621

Text #2

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.6874. Min Act: -0.0000

Data Index: 1141509 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5316. Min Act: -0.0000

Data Index: 1592252 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4347. Min Act: -0.0001

Data Index: 1556595 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4922. Min Act: -0.0001

Data Index: 1581651 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5787. Min Act: -0.0000

Data Index: 1473865 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.6249. Min Act: -0.0000

Data Index: 1471060 (Python Code)

Max Activating Token Index: 921

Text #8

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4446. Min Act: -0.0001

Data Index: 1651643 (Python Code)

Max Activating Token Index: 890

Text #9

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4587. Min Act: -0.0001

Data Index: 1608421 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1651946 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5868. Min Act: -0.0001

Data Index: 1489096 (Python Code)

Max Activating Token Index: 478

Text #12

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5365. Min Act: -0.0001

Data Index: 674990 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4930. Min Act: -0.0001

Data Index: 613557 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1385853 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.6075. Min Act: -0.0001

Data Index: 1441170 (Python Code)

Max Activating Token Index: 663

Text #16

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.6318. Min Act: -0.0000

Data Index: 1551609 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4977. Min Act: -0.0001

Data Index: 355068 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5218. Min Act: -0.0001

Data Index: 1430209 (Python Code)

Max Activating Token Index: 721

Text #19

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1645872 (Python Code)

Max Activating Token Index: 918