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

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

Neuron 181 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1350. Min Range: -3.1350

Max Act: 3.1350. Min Act: -0.1700

Data Index: 1501165 (Python Code)

Max Activating Token Index: 815

Text #1

Max Range: 3.1350. Min Range: -3.1350

Max Act: 3.1034. Min Act: -0.1700

Data Index: 100350 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 3.1350. Min Range: -3.1350

Max Act: 3.0245. Min Act: -0.1700

Data Index: 1512185 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 3.1350. Min Range: -3.1350

Max Act: 3.0087. Min Act: -0.1700

Data Index: 823549 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 3.1350. Min Range: -3.1350

Max Act: 3.0087. Min Act: -0.1700

Data Index: 1578065 (Python Code)

Max Activating Token Index: 905

Text #5

Max Range: 3.1350. Min Range: -3.1350

Max Act: 3.0087. Min Act: -0.1700

Data Index: 1520713 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9929. Min Act: -0.1700

Data Index: 1189375 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9771. Min Act: -0.1700

Data Index: 160668 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9771. Min Act: -0.1700

Data Index: 913894 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9771. Min Act: -0.1700

Data Index: 1308407 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9613. Min Act: -0.1700

Data Index: 234888 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 3.1350. Min Range: -3.1350

Max Act: 3.0087. Min Act: -0.1700

Data Index: 779522 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9613. Min Act: -0.1700

Data Index: 1379869 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9454. Min Act: -0.1700

Data Index: 1521645 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9454. Min Act: -0.1700

Data Index: 980696 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9613. Min Act: -0.1700

Data Index: 1268378 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9454. Min Act: -0.1700

Data Index: 144005 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9454. Min Act: -0.1700

Data Index: 1464474 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9454. Min Act: -0.1700

Data Index: 1419387 (Python Code)

Max Activating Token Index: 376

Text #19

Max Range: 3.1350. Min Range: -3.1350

Max Act: 2.9454. Min Act: -0.1700

Data Index: 454818 (C4 (Web Text))

Max Activating Token Index: 12