Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 992 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0003

Data Index: 786308 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0642. Min Act: -0.0003

Data Index: 942217 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0625. Min Act: -0.0003

Data Index: 100423 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0525. Min Act: -0.0003

Data Index: 396733 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1302674 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0496. Min Act: -0.0003

Data Index: 965312 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1352114 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0470. Min Act: -0.0003

Data Index: 896913 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0484. Min Act: -0.0003

Data Index: 826417 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0473. Min Act: -0.0002

Data Index: 600636 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0458. Min Act: -0.0003

Data Index: 587939 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0498. Min Act: -0.0003

Data Index: 333106 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0454. Min Act: -0.0003

Data Index: 905743 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0473. Min Act: -0.0003

Data Index: 907062 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0463. Min Act: -0.0003

Data Index: 915339 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0471. Min Act: -0.0003

Data Index: 33567 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0437. Min Act: -0.0003

Data Index: 315002 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1043843 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0431. Min Act: -0.0003

Data Index: 23307 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1295693 (C4 (Web Text))

Max Activating Token Index: 1014