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

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

Neuron 271 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: 3.3323. Min Range: -3.3323

Max Act: 3.3323. Min Act: -0.1700

Data Index: 1599060 (Python Code)

Max Activating Token Index: 807

Text #1

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.3009. Min Act: -0.1700

Data Index: 1618927 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.2695. Min Act: -0.1700

Data Index: 336628 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.2066. Min Act: -0.1700

Data Index: 1461081 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.1437. Min Act: -0.1700

Data Index: 630265 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1647591 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.1752. Min Act: -0.1700

Data Index: 1552989 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1477349 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.1594. Min Act: -0.1700

Data Index: 902336 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0648. Min Act: -0.1700

Data Index: 1584807 (Python Code)

Max Activating Token Index: 730

Text #10

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.1122. Min Act: -0.1700

Data Index: 687471 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0964. Min Act: -0.1700

Data Index: 1428793 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0648. Min Act: -0.1700

Data Index: 1515908 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0806. Min Act: -0.1700

Data Index: 868093 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0648. Min Act: -0.1700

Data Index: 661561 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0648. Min Act: -0.1700

Data Index: 989966 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0806. Min Act: -0.1700

Data Index: 1404303 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0806. Min Act: -0.1700

Data Index: 1363919 (Python Code)

Max Activating Token Index: 641

Text #18

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0964. Min Act: -0.1700

Data Index: 1485886 (Python Code)

Max Activating Token Index: 102

Text #19

Max Range: 3.3323. Min Range: -3.3323

Max Act: 3.0806. Min Act: -0.1700

Data Index: 15337 (C4 (Web Text))

Max Activating Token Index: 542