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

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

Neuron 1905 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.5414. Min Act: -0.1700

Data Index: 313153 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.3852. Min Act: -0.1700

Data Index: 111546 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.3852. Min Act: -0.1700

Data Index: 1606008 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.2914. Min Act: -0.1700

Data Index: 785275 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.2602. Min Act: -0.1700

Data Index: 1497934 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.2602. Min Act: -0.1700

Data Index: 775009 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1352. Min Act: -0.1700

Data Index: 1387420 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1977. Min Act: -0.1700

Data Index: 1565660 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1039. Min Act: -0.1700

Data Index: 1482863 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1039. Min Act: -0.1700

Data Index: 1449853 (Python Code)

Max Activating Token Index: 526

Text #10

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1977. Min Act: -0.1700

Data Index: 1398605 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.0727. Min Act: -0.1700

Data Index: 1599828 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1352. Min Act: -0.1700

Data Index: 75851 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1664. Min Act: -0.1700

Data Index: 1595427 (Python Code)

Max Activating Token Index: 417

Text #14

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1039. Min Act: -0.1700

Data Index: 1590986 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1352. Min Act: -0.1700

Data Index: 1370272 (Python Code)

Max Activating Token Index: 553

Text #16

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1352. Min Act: -0.1700

Data Index: 1437293 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1039. Min Act: -0.1700

Data Index: 1579143 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1039. Min Act: -0.1700

Data Index: 1513039 (Python Code)

Max Activating Token Index: 515

Text #19

Max Range: 5.5414. Min Range: -5.5414

Max Act: 5.1039. Min Act: -0.1700

Data Index: 68501 (C4 (Web Text))

Max Activating Token Index: 446