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

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

Neuron 2444 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: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0000

Data Index: 280030 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0601. Min Act: -0.0000

Data Index: 464407 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0663. Min Act: -0.0000

Data Index: 227530 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0641. Min Act: -0.0000

Data Index: 601437 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0611. Min Act: -0.0000

Data Index: 188425 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0626. Min Act: -0.0000

Data Index: 998503 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1056811 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0525. Min Act: -0.0000

Data Index: 916754 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0656. Min Act: -0.0000

Data Index: 921222 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0568. Min Act: -0.0000

Data Index: 907001 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1136146 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1240175 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0562. Min Act: -0.0000

Data Index: 382612 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1149914 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0560. Min Act: -0.0000

Data Index: 718999 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0517. Min Act: -0.0000

Data Index: 800737 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1013948 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1404937 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0572. Min Act: -0.0000

Data Index: 377456 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0521. Min Act: -0.0000

Data Index: 411671 (C4 (Web Text))

Max Activating Token Index: 302