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

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

Neuron 4815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0661. Min Act: -0.0000

Data Index: 137882 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1173644 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1012952 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0475. Min Act: -0.0000

Data Index: 868888 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1202645 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0519. Min Act: -0.0000

Data Index: 411828 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0506. Min Act: -0.0000

Data Index: 844549 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1106759 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0476. Min Act: -0.0000

Data Index: 710757 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0484. Min Act: -0.0000

Data Index: 800701 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0513. Min Act: -0.0000

Data Index: 524132 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0487. Min Act: -0.0000

Data Index: 608308 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0508. Min Act: -0.0000

Data Index: 404082 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0483. Min Act: -0.0000

Data Index: 439896 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0473. Min Act: -0.0000

Data Index: 358372 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0470. Min Act: -0.0000

Data Index: 688872 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0469. Min Act: -0.0000

Data Index: 952979 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1173907 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0455. Min Act: -0.0000

Data Index: 1330747 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1067148 (C4 (Web Text))

Max Activating Token Index: 591