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

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

Neuron 4095 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1055. Min Act: -0.0000

Data Index: 698337 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0851. Min Act: -0.0000

Data Index: 525504 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0855. Min Act: -0.0000

Data Index: 764029 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0808. Min Act: -0.0000

Data Index: 834773 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1033366 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1092259 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0877. Min Act: -0.0000

Data Index: 324307 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0752. Min Act: -0.0000

Data Index: 774839 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1294033 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0692. Min Act: -0.0000

Data Index: 683286 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0692. Min Act: -0.0000

Data Index: 33332 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0693. Min Act: -0.0000

Data Index: 859292 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1019538 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0669. Min Act: -0.0000

Data Index: 147703 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1483897 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0648. Min Act: -0.0000

Data Index: 217580 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1182439 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1350856 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0668. Min Act: -0.0000

Data Index: 881475 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0613. Min Act: -0.0000

Data Index: 737337 (C4 (Web Text))

Max Activating Token Index: 746