Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 783 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1317. Min Range: -3.1317

Max Act: 3.1317. Min Act: -0.1700

Data Index: 1438310 (Python Code)

Max Activating Token Index: 733

Text #1

Max Range: 3.1317. Min Range: -3.1317

Max Act: 3.0991. Min Act: -0.1700

Data Index: 1614621 (Python Code)

Max Activating Token Index: 679

Text #2

Max Range: 3.1317. Min Range: -3.1317

Max Act: 3.1028. Min Act: -0.1700

Data Index: 1428247 (Python Code)

Max Activating Token Index: 379

Text #3

Max Range: 3.1317. Min Range: -3.1317

Max Act: 3.0666. Min Act: -0.1700

Data Index: 1427382 (Python Code)

Max Activating Token Index: 588

Text #4

Max Range: 3.1317. Min Range: -3.1317

Max Act: 3.0668. Min Act: -0.1700

Data Index: 1531803 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 3.1317. Min Range: -3.1317

Max Act: 3.0636. Min Act: -0.1700

Data Index: 1525073 (Python Code)

Max Activating Token Index: 342

Text #6

Max Range: 3.1317. Min Range: -3.1317

Max Act: 3.0006. Min Act: -0.1700

Data Index: 1538231 (Python Code)

Max Activating Token Index: 359

Text #7

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9897. Min Act: -0.1700

Data Index: 1623881 (Python Code)

Max Activating Token Index: 381

Text #8

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9884. Min Act: -0.1700

Data Index: 1411022 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9923. Min Act: -0.1700

Data Index: 1589047 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9612. Min Act: -0.1700

Data Index: 1362822 (Python Code)

Max Activating Token Index: 704

Text #11

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9719. Min Act: -0.1700

Data Index: 1419998 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9713. Min Act: -0.1700

Data Index: 1398203 (Python Code)

Max Activating Token Index: 459

Text #13

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9654. Min Act: -0.1700

Data Index: 1493382 (Python Code)

Max Activating Token Index: 775

Text #14

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9670. Min Act: -0.1700

Data Index: 1618829 (Python Code)

Max Activating Token Index: 921

Text #15

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9832. Min Act: -0.1700

Data Index: 1379922 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9494. Min Act: -0.1700

Data Index: 1464321 (Python Code)

Max Activating Token Index: 647

Text #17

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9533. Min Act: -0.1700

Data Index: 1433125 (Python Code)

Max Activating Token Index: 571

Text #18

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9632. Min Act: -0.1700

Data Index: 1411533 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 3.1317. Min Range: -3.1317

Max Act: 2.9541. Min Act: -0.1700

Data Index: 1418907 (Python Code)

Max Activating Token Index: 994