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

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

Neuron 1581 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.6358. Min Act: -0.1700

Data Index: 1543822 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.4483. Min Act: -0.1700

Data Index: 1614142 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.2608. Min Act: -0.1700

Data Index: 1400550 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.2608. Min Act: -0.1700

Data Index: 1649713 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1671. Min Act: -0.1700

Data Index: 918534 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1983. Min Act: -0.1699

Data Index: 1070501 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.0733. Min Act: -0.1700

Data Index: 1466813 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1358. Min Act: -0.1700

Data Index: 1450156 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1046. Min Act: -0.1700

Data Index: 1437250 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1671. Min Act: -0.1699

Data Index: 49738 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.0733. Min Act: -0.1700

Data Index: 1505766 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1358. Min Act: -0.1700

Data Index: 105203 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.0733. Min Act: -0.1700

Data Index: 583482 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1046. Min Act: -0.1700

Data Index: 680709 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1358. Min Act: -0.1700

Data Index: 1584395 (Python Code)

Max Activating Token Index: 839

Text #15

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1046. Min Act: -0.1700

Data Index: 1606789 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.0421. Min Act: -0.1700

Data Index: 1491011 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.1046. Min Act: -0.1700

Data Index: 1460023 (Python Code)

Max Activating Token Index: 837

Text #18

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.0733. Min Act: -0.1700

Data Index: 1624798 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 5.6358. Min Range: -5.6358

Max Act: 5.0733. Min Act: -0.1700

Data Index: 1612627 (Python Code)

Max Activating Token Index: 358