Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1666 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0492. Min Act: -0.0006

Data Index: 827798 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0488. Min Act: -0.0006

Data Index: 469199 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0458. Min Act: -0.0006

Data Index: 708198 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0446. Min Act: -0.0006

Data Index: 442698 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0416. Min Act: -0.0006

Data Index: 893347 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0427. Min Act: -0.0006

Data Index: 67444 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0407. Min Act: -0.0006

Data Index: 506806 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0419. Min Act: -0.0006

Data Index: 480723 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0417. Min Act: -0.0006

Data Index: 904320 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0427. Min Act: -0.0006

Data Index: 483391 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0404. Min Act: -0.0006

Data Index: 550260 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0403. Min Act: -0.0006

Data Index: 154475 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0409. Min Act: -0.0006

Data Index: 194707 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1325571 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1086228 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0397. Min Act: -0.0006

Data Index: 1624121 (Python Code)

Max Activating Token Index: 331

Text #16

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0388. Min Act: -0.0006

Data Index: 813210 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1105021 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0405. Min Act: -0.0006

Data Index: 85735 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0492. Min Range: -0.0492

Max Act: 0.0410. Min Act: -0.0006

Data Index: 535208 (C4 (Web Text))

Max Activating Token Index: 889