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

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

Neuron 3636 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1422228 (Python Code)

Max Activating Token Index: 499

Text #1

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8684. Min Act: -0.0000

Data Index: 496721 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1407894 (Python Code)

Max Activating Token Index: 556

Text #3

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1610384 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1433096 (Python Code)

Max Activating Token Index: 112

Text #5

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.8531. Min Act: -0.0000

Data Index: 155579 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1597599 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1597162 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7705. Min Act: -0.0000

Data Index: 342967 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1363709 (Python Code)

Max Activating Token Index: 1004

Text #10

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1463582 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7402. Min Act: -0.0000

Data Index: 936984 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7307. Min Act: -0.0000

Data Index: 817687 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7559. Min Act: -0.0000

Data Index: 23162 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1629600 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1509638 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1653131 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1631245 (Python Code)

Max Activating Token Index: 972

Text #18

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6605. Min Act: -0.0000

Data Index: 984657 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.9633. Min Range: -0.9633

Max Act: 0.6401. Min Act: -0.0000

Data Index: 866759 (C4 (Web Text))

Max Activating Token Index: 984