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

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

Neuron 957 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: 5.2979. Min Range: -5.2979

Max Act: 5.2745. Min Act: -0.1700

Data Index: 1079675 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.2979. Min Act: -0.1700

Data Index: 273451 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.2276. Min Act: -0.1700

Data Index: 877912 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.2276. Min Act: -0.1700

Data Index: 1289924 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.1808. Min Act: -0.1700

Data Index: 799537 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.1573. Min Act: -0.1700

Data Index: 731522 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.1651. Min Act: -0.1700

Data Index: 972740 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.1104. Min Act: -0.1700

Data Index: 175594 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.1026. Min Act: -0.1700

Data Index: 470246 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.1183. Min Act: -0.1700

Data Index: 932795 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0948. Min Act: -0.1700

Data Index: 1109601 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0948. Min Act: -0.1700

Data Index: 778644 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0792. Min Act: -0.1700

Data Index: 174248 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0948. Min Act: -0.1700

Data Index: 1342117 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0401. Min Act: -0.1700

Data Index: 875852 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0558. Min Act: -0.1700

Data Index: 1112514 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0011. Min Act: -0.1700

Data Index: 780448 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0089. Min Act: -0.1700

Data Index: 483454 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0323. Min Act: -0.1700

Data Index: 87067 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 5.2979. Min Range: -5.2979

Max Act: 5.0245. Min Act: -0.1700

Data Index: 914073 (C4 (Web Text))

Max Activating Token Index: 735