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

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

Neuron 527 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: 5.8639. Min Range: -5.8639

Max Act: 5.8639. Min Act: -0.1700

Data Index: 1385928 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.8171. Min Act: -0.1700

Data Index: 1491318 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7233. Min Act: -0.1700

Data Index: 1497133 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7233. Min Act: -0.1700

Data Index: 1515161 (Python Code)

Max Activating Token Index: 1002

Text #4

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7389. Min Act: -0.1700

Data Index: 1445051 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7389. Min Act: -0.1700

Data Index: 1439293 (Python Code)

Max Activating Token Index: 961

Text #6

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7389. Min Act: -0.1700

Data Index: 1517023 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7546. Min Act: -0.1700

Data Index: 1528301 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7077. Min Act: -0.1700

Data Index: 1494962 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6921. Min Act: -0.1700

Data Index: 211913 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.7077. Min Act: -0.1700

Data Index: 804089 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6764. Min Act: -0.1700

Data Index: 1564114 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6921. Min Act: -0.1700

Data Index: 1642486 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6921. Min Act: -0.1700

Data Index: 1427588 (Python Code)

Max Activating Token Index: 946

Text #14

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6608. Min Act: -0.1700

Data Index: 1537839 (Python Code)

Max Activating Token Index: 908

Text #15

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6608. Min Act: -0.1700

Data Index: 1557612 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6764. Min Act: -0.1700

Data Index: 1375837 (Python Code)

Max Activating Token Index: 614

Text #17

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6764. Min Act: -0.1700

Data Index: 1513336 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6139. Min Act: -0.1700

Data Index: 1425171 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 5.8639. Min Range: -5.8639

Max Act: 5.6452. Min Act: -0.1700

Data Index: 1569477 (Python Code)

Max Activating Token Index: 774