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

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

Neuron 266 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: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0003

Data Index: 966727 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1098578 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1561954 (Python Code)

Max Activating Token Index: 865

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0545. Min Act: -0.0002

Data Index: 860955 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0561. Min Act: -0.0004

Data Index: 468367 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0543. Min Act: -0.0003

Data Index: 112377 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0497. Min Act: -0.0003

Data Index: 362222 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0529. Min Act: -0.0003

Data Index: 521735 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1275412 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0477. Min Act: -0.0004

Data Index: 362041 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0461. Min Act: -0.0003

Data Index: 797238 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0437. Min Act: -0.0003

Data Index: 569771 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0471. Min Act: -0.0003

Data Index: 700901 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1147928 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0425. Min Act: -0.0003

Data Index: 779935 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0438. Min Act: -0.0003

Data Index: 213309 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0453. Min Act: -0.0003

Data Index: 349997 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1178582 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0425. Min Act: -0.0003

Data Index: 995100 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1114393 (C4 (Web Text))

Max Activating Token Index: 1021