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

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

Neuron 468 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.1636. Min Act: -0.1700

Data Index: 1326056 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.1321. Min Act: -0.1700

Data Index: 1047422 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.1479. Min Act: -0.1700

Data Index: 51272 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.1164. Min Act: -0.1700

Data Index: 624645 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.1321. Min Act: -0.1700

Data Index: 847106 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.1164. Min Act: -0.1700

Data Index: 414077 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.1006. Min Act: -0.1700

Data Index: 1118211 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0849. Min Act: -0.1700

Data Index: 498438 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0691. Min Act: -0.1700

Data Index: 962629 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0691. Min Act: -0.1700

Data Index: 285128 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0533. Min Act: -0.1700

Data Index: 423488 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0375. Min Act: -0.1700

Data Index: 611980 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0217. Min Act: -0.1700

Data Index: 175927 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0059. Min Act: -0.1700

Data Index: 950688 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0217. Min Act: -0.1700

Data Index: 570636 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0059. Min Act: -0.1700

Data Index: 1277327 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 3.1636. Min Range: -3.1636

Max Act: 2.9901. Min Act: -0.1700

Data Index: 51173 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 3.1636. Min Range: -3.1636

Max Act: 3.0059. Min Act: -0.1700

Data Index: 1098368 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 3.1636. Min Range: -3.1636

Max Act: 2.9901. Min Act: -0.1700

Data Index: 733780 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 3.1636. Min Range: -3.1636

Max Act: 2.9743. Min Act: -0.1700

Data Index: 952880 (C4 (Web Text))

Max Activating Token Index: 326