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

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

Neuron 1426 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1122522 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0006

Data Index: 308330 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0466. Min Act: -0.0006

Data Index: 26331 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0454. Min Act: -0.0006

Data Index: 1197542 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0441. Min Act: -0.0006

Data Index: 1256061 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0432. Min Act: -0.0006

Data Index: 114300 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0429. Min Act: -0.0006

Data Index: 594031 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0426. Min Act: -0.0006

Data Index: 1061030 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0425. Min Act: -0.0006

Data Index: 180032 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0405. Min Act: -0.0006

Data Index: 1055749 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0422. Min Act: -0.0006

Data Index: 910237 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0421. Min Act: -0.0006

Data Index: 611865 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0396. Min Act: -0.0006

Data Index: 117947 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0395. Min Act: -0.0006

Data Index: 127641 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0410. Min Act: -0.0006

Data Index: 1299754 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0397. Min Act: -0.0006

Data Index: 240373 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1214107 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0397. Min Act: -0.0006

Data Index: 1264973 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0413. Min Act: -0.0006

Data Index: 145583 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0403. Min Act: -0.0006

Data Index: 30293 (C4 (Web Text))

Max Activating Token Index: 321