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

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

Neuron 338 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.5852. Min Act: -0.1700

Data Index: 812718 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.5382. Min Act: -0.1700

Data Index: 1610091 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4755. Min Act: -0.1700

Data Index: 175946 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3814. Min Act: -0.1700

Data Index: 1476285 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4598. Min Act: -0.1700

Data Index: 1374700 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.5068. Min Act: -0.1700

Data Index: 1465257 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4285. Min Act: -0.1700

Data Index: 1650767 (Python Code)

Max Activating Token Index: 653

Text #7

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3814. Min Act: -0.1700

Data Index: 1540994 (Python Code)

Max Activating Token Index: 822

Text #8

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4285. Min Act: -0.1700

Data Index: 1444200 (Python Code)

Max Activating Token Index: 853

Text #9

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4128. Min Act: -0.1700

Data Index: 1504293 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4128. Min Act: -0.1700

Data Index: 1399880 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.4128. Min Act: -0.1700

Data Index: 1581872 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3971. Min Act: -0.1700

Data Index: 1024004 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3814. Min Act: -0.1700

Data Index: 1471734 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3657. Min Act: -0.1700

Data Index: 1633720 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3657. Min Act: -0.1700

Data Index: 1632138 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3971. Min Act: -0.1700

Data Index: 1586063 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3657. Min Act: -0.1700

Data Index: 1421540 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3657. Min Act: -0.1700

Data Index: 1447533 (Python Code)

Max Activating Token Index: 454

Text #19

Max Range: 3.5852. Min Range: -3.5852

Max Act: 3.3657. Min Act: -0.1700

Data Index: 1574908 (Python Code)

Max Activating Token Index: 769