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

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

Neuron 1587 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.3371. Min Act: -0.1700

Data Index: 637083 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.3057. Min Act: -0.1700

Data Index: 233087 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2900. Min Act: -0.1700

Data Index: 202504 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2429. Min Act: -0.1700

Data Index: 649067 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.2114. Min Act: -0.1700

Data Index: 788045 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1800. Min Act: -0.1700

Data Index: 1344375 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1327. Min Act: -0.1700

Data Index: 1246935 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1485. Min Act: -0.1700

Data Index: 343926 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1170. Min Act: -0.1700

Data Index: 481724 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1170. Min Act: -0.1700

Data Index: 283438 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1485. Min Act: -0.1700

Data Index: 519664 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1170. Min Act: -0.1700

Data Index: 272176 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1170. Min Act: -0.1700

Data Index: 307765 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.0854. Min Act: -0.1700

Data Index: 1116838 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1170. Min Act: -0.1700

Data Index: 709875 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1485. Min Act: -0.1700

Data Index: 729497 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.0854. Min Act: -0.1700

Data Index: 39971 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1170. Min Act: -0.1700

Data Index: 251906 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.0539. Min Act: -0.1700

Data Index: 209064 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 3.3371. Min Range: -3.3371

Max Act: 3.1012. Min Act: -0.1700

Data Index: 1239988 (C4 (Web Text))

Max Activating Token Index: 75