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

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

Neuron 603 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: 3.8691. Min Range: -3.8691

Max Act: 3.8691. Min Act: -0.1700

Data Index: 1628122 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.8066. Min Act: -0.1700

Data Index: 1390583 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.8379. Min Act: -0.1700

Data Index: 1376351 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.8379. Min Act: -0.1700

Data Index: 1550797 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.8066. Min Act: -0.1700

Data Index: 1644205 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.8066. Min Act: -0.1700

Data Index: 1573004 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.8066. Min Act: -0.1700

Data Index: 1576899 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7440. Min Act: -0.1700

Data Index: 1521514 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7440. Min Act: -0.1700

Data Index: 1616991 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7440. Min Act: -0.1700

Data Index: 1407067 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1632834 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7440. Min Act: -0.1700

Data Index: 1640961 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1587529 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1558784 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.6814. Min Act: -0.1700

Data Index: 1509969 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1451532 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1479119 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.6814. Min Act: -0.1700

Data Index: 1438554 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1380337 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 3.8691. Min Range: -3.8691

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1432751 (Python Code)

Max Activating Token Index: 88