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

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

Neuron 1620 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: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0005

Data Index: 1298711 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0475. Min Act: -0.0005

Data Index: 856259 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0455. Min Act: -0.0005

Data Index: 1209255 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0458. Min Act: -0.0005

Data Index: 882701 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0444. Min Act: -0.0005

Data Index: 59544 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0471. Min Act: -0.0005

Data Index: 1282356 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0433. Min Act: -0.0005

Data Index: 627885 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0438. Min Act: -0.0005

Data Index: 716492 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0403. Min Act: -0.0005

Data Index: 1210129 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0422. Min Act: -0.0005

Data Index: 444922 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0456. Min Act: -0.0005

Data Index: 6806 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0413. Min Act: -0.0005

Data Index: 926901 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0404. Min Act: -0.0005

Data Index: 310108 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0456. Min Act: -0.0005

Data Index: 165957 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0431. Min Act: -0.0005

Data Index: 466665 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0414. Min Act: -0.0005

Data Index: 595551 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0397. Min Act: -0.0005

Data Index: 1057126 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0427. Min Act: -0.0005

Data Index: 707077 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0399. Min Act: -0.0005

Data Index: 898853 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0385. Min Act: -0.0005

Data Index: 1011155 (C4 (Web Text))

Max Activating Token Index: 881