Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4024 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3645. Min Act: -0.0001

Data Index: 189034 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3042. Min Act: -0.0001

Data Index: 83201 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.3119. Min Act: -0.0000

Data Index: 974571 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2757. Min Act: -0.0000

Data Index: 397356 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2752. Min Act: -0.0000

Data Index: 939664 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2786. Min Act: -0.0000

Data Index: 723350 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2590. Min Act: -0.0000

Data Index: 370422 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2645. Min Act: -0.0001

Data Index: 342369 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2637. Min Act: -0.0000

Data Index: 451189 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2772. Min Act: -0.0001

Data Index: 38651 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2568. Min Act: -0.0001

Data Index: 877614 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2506. Min Act: -0.0001

Data Index: 976185 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2506. Min Act: -0.0001

Data Index: 1107375 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2562. Min Act: -0.0000

Data Index: 312400 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2366. Min Act: -0.0000

Data Index: 35097 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2434. Min Act: -0.0001

Data Index: 1648190 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2422. Min Act: -0.0001

Data Index: 998886 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2404. Min Act: -0.0000

Data Index: 995885 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2417. Min Act: -0.0001

Data Index: 1179691 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.3645. Min Range: -0.3645

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1631188 (Python Code)

Max Activating Token Index: 962