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

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

Neuron 540 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: 0.0491. Min Range: -0.0491

Max Act: 0.0491. Min Act: -0.0002

Data Index: 682720 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0443. Min Act: -0.0002

Data Index: 695153 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0430. Min Act: -0.0002

Data Index: 910475 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0437. Min Act: -0.0003

Data Index: 486198 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0409. Min Act: -0.0002

Data Index: 995775 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0404. Min Act: -0.0001

Data Index: 61734 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0387. Min Act: -0.0002

Data Index: 268769 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0394. Min Act: -0.0002

Data Index: 787472 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0390. Min Act: -0.0001

Data Index: 181855 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0381. Min Act: -0.0003

Data Index: 195246 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1264101 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0396. Min Act: -0.0002

Data Index: 646977 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1237603 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0374. Min Act: -0.0002

Data Index: 3315 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0379. Min Act: -0.0002

Data Index: 343985 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0377. Min Act: -0.0002

Data Index: 466048 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0377. Min Act: -0.0002

Data Index: 443026 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0373. Min Act: -0.0001

Data Index: 176541 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0369. Min Act: -0.0002

Data Index: 419454 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.0491. Min Range: -0.0491

Max Act: 0.0366. Min Act: -0.0003

Data Index: 728505 (C4 (Web Text))

Max Activating Token Index: 247