Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2844 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0540. Min Act: -0.0004

Data Index: 775452 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0004

Data Index: 809887 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0492. Min Act: -0.0004

Data Index: 475069 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0457. Min Act: -0.0004

Data Index: 806510 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0412. Min Act: -0.0004

Data Index: 498630 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0402. Min Act: -0.0004

Data Index: 1046917 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0371. Min Act: -0.0004

Data Index: 684908 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0348. Min Act: -0.0004

Data Index: 414823 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0379. Min Act: -0.0004

Data Index: 1007968 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0414. Min Act: -0.0004

Data Index: 249040 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0432. Min Act: -0.0004

Data Index: 501804 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0348. Min Act: -0.0004

Data Index: 237854 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0303. Min Act: -0.0004

Data Index: 794070 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0465. Min Act: -0.0004

Data Index: 430257 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0357. Min Act: -0.0004

Data Index: 350525 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0346. Min Act: -0.0004

Data Index: 942759 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0275. Min Act: -0.0004

Data Index: 356661 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0300. Min Act: -0.0004

Data Index: 153218 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0459. Min Act: -0.0004

Data Index: 1105438 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0346. Min Act: -0.0004

Data Index: 567666 (C4 (Web Text))

Max Activating Token Index: 678