Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 860 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.2662. Min Act: -0.1699

Data Index: 1391941 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.3287. Min Act: -0.1699

Data Index: 230995 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.2194. Min Act: -0.1699

Data Index: 1407376 (Python Code)

Max Activating Token Index: 584

Text #3

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.2662. Min Act: -0.1699

Data Index: 828078 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.3444. Min Act: -0.1699

Data Index: 1526331 (Python Code)

Max Activating Token Index: 495

Text #5

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.1725. Min Act: -0.1699

Data Index: 40687 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.1256. Min Act: -0.1699

Data Index: 1637809 (Python Code)

Max Activating Token Index: 525

Text #7

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.0944. Min Act: -0.1699

Data Index: 1246249 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.0944. Min Act: -0.1699

Data Index: 1079100 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.1256. Min Act: -0.1699

Data Index: 1188334 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.0475. Min Act: -0.1699

Data Index: 729772 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.9850. Min Act: -0.1699

Data Index: 1486000 (Python Code)

Max Activating Token Index: 738

Text #12

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.1256. Min Act: -0.1699

Data Index: 1642562 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.0162. Min Act: -0.1699

Data Index: 304607 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.0319. Min Act: -0.1699

Data Index: 1604046 (Python Code)

Max Activating Token Index: 385

Text #15

Max Range: 7.3444. Min Range: -7.3444

Max Act: 7.0006. Min Act: -0.1699

Data Index: 708480 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.8912. Min Act: -0.1699

Data Index: 711445 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.9225. Min Act: -0.1699

Data Index: 1287311 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.8444. Min Act: -0.1699

Data Index: 1160689 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 7.3444. Min Range: -7.3444

Max Act: 6.8600. Min Act: -0.1699

Data Index: 745160 (C4 (Web Text))

Max Activating Token Index: 357