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

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

Neuron 1291 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1487258 (Python Code)

Max Activating Token Index: 979

Text #1

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4075. Min Act: -0.0000

Data Index: 632264 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4045. Min Act: -0.0000

Data Index: 778757 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1478093 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3882. Min Act: -0.0000

Data Index: 720016 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3879. Min Act: -0.0000

Data Index: 487139 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1231579 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3752. Min Act: -0.0000

Data Index: 506850 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3908. Min Act: -0.0000

Data Index: 965241 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3840. Min Act: -0.0000

Data Index: 825939 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3647. Min Act: -0.0000

Data Index: 447287 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3881. Min Act: -0.0000

Data Index: 526157 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1080698 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1540557 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1532030 (Python Code)

Max Activating Token Index: 418

Text #15

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1452658 (Python Code)

Max Activating Token Index: 865

Text #16

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1322374 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1571176 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3513. Min Act: -0.0000

Data Index: 93573 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1185865 (C4 (Web Text))

Max Activating Token Index: 644