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

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

Neuron 4691 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3449. Min Act: -0.0000

Data Index: 358570 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3426. Min Act: -0.0000

Data Index: 678117 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1281320 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3165. Min Act: -0.0000

Data Index: 651173 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1049330 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3110. Min Act: -0.0000

Data Index: 474256 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3049. Min Act: -0.0000

Data Index: 42052 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1492499 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3030. Min Act: -0.0000

Data Index: 813559 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2753. Min Act: -0.0000

Data Index: 228359 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2653. Min Act: -0.0000

Data Index: 57330 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2745. Min Act: -0.0000

Data Index: 555911 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1152193 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1215140 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1470783 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2550. Min Act: -0.0000

Data Index: 660120 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2643. Min Act: -0.0000

Data Index: 573107 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2609. Min Act: -0.0000

Data Index: 144063 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2615. Min Act: -0.0000

Data Index: 149084 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2681. Min Act: -0.0000

Data Index: 891231 (C4 (Web Text))

Max Activating Token Index: 223