Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0572. Min Act: -0.0002

Data Index: 991604 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1319623 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0464. Min Act: -0.0002

Data Index: 286794 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0470. Min Act: -0.0002

Data Index: 906008 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1055136 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0417. Min Act: -0.0002

Data Index: 643008 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0430. Min Act: -0.0002

Data Index: 372575 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1027612 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0410. Min Act: -0.0002

Data Index: 606368 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0430. Min Act: -0.0002

Data Index: 541724 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0413. Min Act: -0.0002

Data Index: 698801 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0412. Min Act: -0.0002

Data Index: 602189 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0417. Min Act: -0.0002

Data Index: 444092 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0403. Min Act: -0.0002

Data Index: 815839 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0419. Min Act: -0.0002

Data Index: 587524 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1015306 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0413. Min Act: -0.0002

Data Index: 428989 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1089837 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0384. Min Act: -0.0002

Data Index: 572220 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0406. Min Act: -0.0002

Data Index: 797599 (C4 (Web Text))

Max Activating Token Index: 781