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

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

Neuron 1071 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.3382. Min Act: -0.1700

Data Index: 1393795 (Python Code)

Max Activating Token Index: 696

Text #1

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.3068. Min Act: -0.1700

Data Index: 1570587 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1477558 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.3068. Min Act: -0.1700

Data Index: 1589346 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.2597. Min Act: -0.1700

Data Index: 1497290 (Python Code)

Max Activating Token Index: 707

Text #5

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.2754. Min Act: -0.1700

Data Index: 1650297 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.2440. Min Act: -0.1700

Data Index: 1555388 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1608542 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.2282. Min Act: -0.1700

Data Index: 1413057 (Python Code)

Max Activating Token Index: 558

Text #9

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1563355 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1390568 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1810. Min Act: -0.1700

Data Index: 1444322 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1653. Min Act: -0.1700

Data Index: 1431132 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1968. Min Act: -0.1700

Data Index: 1394198 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1495. Min Act: -0.1700

Data Index: 1541539 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1810. Min Act: -0.1700

Data Index: 734476 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1023. Min Act: -0.1700

Data Index: 485438 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1495. Min Act: -0.1700

Data Index: 1568661 (Python Code)

Max Activating Token Index: 416

Text #18

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1653. Min Act: -0.1700

Data Index: 961586 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 3.3382. Min Range: -3.3382

Max Act: 3.1495. Min Act: -0.1700

Data Index: 1369509 (Python Code)

Max Activating Token Index: 1019