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

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

Neuron 1961 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0005

Data Index: 365598 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0432. Min Act: -0.0005

Data Index: 687651 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0438. Min Act: -0.0005

Data Index: 758605 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0429. Min Act: -0.0005

Data Index: 842094 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0417. Min Act: -0.0005

Data Index: 761404 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0417. Min Act: -0.0005

Data Index: 702318 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0404. Min Act: -0.0005

Data Index: 1328234 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0409. Min Act: -0.0005

Data Index: 1004930 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0400. Min Act: -0.0005

Data Index: 1193486 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0405. Min Act: -0.0005

Data Index: 619927 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0395. Min Act: -0.0005

Data Index: 155749 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0392. Min Act: -0.0005

Data Index: 113645 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0384. Min Act: -0.0005

Data Index: 804581 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0398. Min Act: -0.0005

Data Index: 631162 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1202742 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0381. Min Act: -0.0005

Data Index: 82836 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0389. Min Act: -0.0005

Data Index: 777842 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0379. Min Act: -0.0005

Data Index: 516099 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0385. Min Act: -0.0005

Data Index: 75653 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0388. Min Act: -0.0005

Data Index: 168469 (C4 (Web Text))

Max Activating Token Index: 323