Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2976 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2406. Min Act: -0.0001

Data Index: 654747 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1840. Min Act: -0.0001

Data Index: 827776 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1889. Min Act: -0.0001

Data Index: 716057 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1608. Min Act: -0.0001

Data Index: 831895 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1665. Min Act: -0.0001

Data Index: 968468 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1570. Min Act: -0.0001

Data Index: 381328 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1598. Min Act: -0.0001

Data Index: 959010 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1462. Min Act: -0.0001

Data Index: 1219668 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1519. Min Act: -0.0001

Data Index: 703926 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1452. Min Act: -0.0001

Data Index: 518127 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1493. Min Act: -0.0001

Data Index: 633103 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1200678 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1450. Min Act: -0.0001

Data Index: 544767 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1268515 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1423. Min Act: -0.0001

Data Index: 191397 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1012226 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1374. Min Act: -0.0001

Data Index: 474223 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1299533 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1382. Min Act: -0.0001

Data Index: 861212 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1372. Min Act: -0.0001

Data Index: 558654 (C4 (Web Text))

Max Activating Token Index: 821