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

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

Neuron 2235 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1119958 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2932. Min Act: -0.0000

Data Index: 467501 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2872. Min Act: -0.0000

Data Index: 632172 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1045573 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1066774 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2698. Min Act: -0.0000

Data Index: 650126 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2585. Min Act: -0.0000

Data Index: 212551 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2591. Min Act: -0.0000

Data Index: 631474 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2636. Min Act: -0.0000

Data Index: 645457 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2756. Min Act: -0.0000

Data Index: 191760 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2603. Min Act: -0.0001

Data Index: 223873 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1134010 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2612. Min Act: -0.0000

Data Index: 603073 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2597. Min Act: -0.0001

Data Index: 613157 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2593. Min Act: -0.0001

Data Index: 559237 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2578. Min Act: -0.0000

Data Index: 893677 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2557. Min Act: -0.0001

Data Index: 380193 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2536. Min Act: -0.0001

Data Index: 383064 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2623. Min Act: -0.0000

Data Index: 719592 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.3561. Min Range: -0.3561

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1056473 (C4 (Web Text))

Max Activating Token Index: 602