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

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

Neuron 2048 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1140024 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0001

Data Index: 723691 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0766. Min Act: -0.0001

Data Index: 505266 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1255891 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0708. Min Act: -0.0001

Data Index: 715539 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0701. Min Act: -0.0001

Data Index: 310525 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0674. Min Act: -0.0001

Data Index: 361494 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0686. Min Act: -0.0001

Data Index: 697874 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0712. Min Act: -0.0001

Data Index: 705949 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1240856 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0728. Min Act: -0.0001

Data Index: 616853 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0671. Min Act: -0.0001

Data Index: 683174 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0672. Min Act: -0.0001

Data Index: 239043 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1247772 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0660. Min Act: -0.0001

Data Index: 619343 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1050304 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0651. Min Act: -0.0001

Data Index: 847632 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0608. Min Act: -0.0001

Data Index: 112957 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0662. Min Act: -0.0001

Data Index: 351758 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0666. Min Act: -0.0001

Data Index: 699597 (C4 (Web Text))

Max Activating Token Index: 3