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

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

Neuron 5514 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.5631. Min Act: -0.0000

Data Index: 436846 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3053. Min Act: -0.0000

Data Index: 43875 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3861. Min Act: -0.0000

Data Index: 52150 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3749. Min Act: -0.0000

Data Index: 46136 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.4009. Min Act: -0.0000

Data Index: 736859 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3512. Min Act: -0.0000

Data Index: 403189 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3381. Min Act: -0.0000

Data Index: 7676 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3457. Min Act: -0.0000

Data Index: 22881 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2456. Min Act: -0.0000

Data Index: 787821 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2498. Min Act: -0.0000

Data Index: 745959 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3050. Min Act: -0.0000

Data Index: 154638 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3547. Min Act: -0.0000

Data Index: 1044626 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2809. Min Act: -0.0000

Data Index: 991215 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1226841 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2565. Min Act: -0.0000

Data Index: 419416 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1043531 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1032576 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1204971 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2322. Min Act: -0.0000

Data Index: 651864 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.1556. Min Act: -0.0000

Data Index: 650586 (C4 (Web Text))

Max Activating Token Index: 194