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

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

Neuron 974 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1355102 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0517. Min Act: -0.0003

Data Index: 937277 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0515. Min Act: -0.0003

Data Index: 815223 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0518. Min Act: -0.0004

Data Index: 1032536 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0474. Min Act: -0.0003

Data Index: 813048 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0480. Min Act: -0.0003

Data Index: 444597 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0485. Min Act: -0.0003

Data Index: 708585 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0486. Min Act: -0.0003

Data Index: 436012 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1097736 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0485. Min Act: -0.0003

Data Index: 231638 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0474. Min Act: -0.0003

Data Index: 825463 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1055242 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0363. Min Act: -0.0003

Data Index: 295615 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1220234 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0429. Min Act: -0.0003

Data Index: 242779 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1020223 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0441. Min Act: -0.0003

Data Index: 466643 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0458. Min Act: -0.0003

Data Index: 709736 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0399. Min Act: -0.0003

Data Index: 476422 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0443. Min Act: -0.0003

Data Index: 897555 (C4 (Web Text))

Max Activating Token Index: 38