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

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

Neuron 1674 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: 7.7204. Min Range: -7.7204

Max Act: 7.7204. Min Act: -0.1700

Data Index: 1423584 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9704. Min Act: -0.1700

Data Index: 367599 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9704. Min Act: -0.1700

Data Index: 800176 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9704. Min Act: -0.1700

Data Index: 539580 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9704. Min Act: -0.1700

Data Index: 1100076 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9704. Min Act: -0.1700

Data Index: 476230 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9079. Min Act: -0.1700

Data Index: 1510213 (Python Code)

Max Activating Token Index: 641

Text #7

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.8454. Min Act: -0.1700

Data Index: 218771 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.5954. Min Act: -0.1700

Data Index: 701694 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.7829. Min Act: -0.1700

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.8454. Min Act: -0.1700

Data Index: 295739 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.7204. Min Act: -0.1700

Data Index: 529404 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9079. Min Act: -0.1700

Data Index: 1256674 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.7829. Min Act: -0.1700

Data Index: 1015551 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.9079. Min Act: -0.1700

Data Index: 215679 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.8454. Min Act: -0.1700

Data Index: 696574 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.7829. Min Act: -0.1700

Data Index: 663141 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.6579. Min Act: -0.1700

Data Index: 1250461 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.6579. Min Act: -0.1700

Data Index: 1141193 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 7.7204. Min Range: -7.7204

Max Act: 6.7829. Min Act: -0.1700

Data Index: 713597 (C4 (Web Text))

Max Activating Token Index: 854