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

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

Neuron 230 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.4341. Min Act: -0.1700

Data Index: 1078840 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.4029. Min Act: -0.1700

Data Index: 947967 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.4966. Min Act: -0.1700

Data Index: 501245 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.3404. Min Act: -0.1700

Data Index: 215322 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.4029. Min Act: -0.1700

Data Index: 214576 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.3091. Min Act: -0.1700

Data Index: 300165 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.2779. Min Act: -0.1700

Data Index: 886497 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.1529. Min Act: -0.1700

Data Index: 353594 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.2154. Min Act: -0.1700

Data Index: 326749 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.1529. Min Act: -0.1700

Data Index: 243986 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.1841. Min Act: -0.1700

Data Index: 1206727 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.1216. Min Act: -0.1700

Data Index: 940432 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.1529. Min Act: -0.1700

Data Index: 182046 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.0904. Min Act: -0.1700

Data Index: 477167 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.0904. Min Act: -0.1700

Data Index: 196531 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.0591. Min Act: -0.1700

Data Index: 616435 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 5.4966. Min Range: -5.4966

Max Act: 4.9966. Min Act: -0.1700

Data Index: 529269 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.0279. Min Act: -0.1700

Data Index: 984547 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 5.4966. Min Range: -5.4966

Max Act: 5.0279. Min Act: -0.1700

Data Index: 1348417 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 5.4966. Min Range: -5.4966

Max Act: 4.9966. Min Act: -0.1700

Data Index: 289316 (C4 (Web Text))

Max Activating Token Index: 498