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

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

Neuron 259 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: 3.9459. Min Range: -3.9459

Max Act: 3.8834. Min Act: -0.1700

Data Index: 1065680 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.9459. Min Act: -0.1700

Data Index: 1423526 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7896. Min Act: -0.1700

Data Index: 1312167 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.8521. Min Act: -0.1700

Data Index: 1496183 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.8834. Min Act: -0.1700

Data Index: 569690 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7583. Min Act: -0.1700

Data Index: 1649079 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7583. Min Act: -0.1700

Data Index: 1520248 (Python Code)

Max Activating Token Index: 384

Text #7

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7896. Min Act: -0.1700

Data Index: 521904 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7583. Min Act: -0.1700

Data Index: 738656 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7270. Min Act: -0.1700

Data Index: 1494339 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7583. Min Act: -0.1700

Data Index: 1585627 (Python Code)

Max Activating Token Index: 950

Text #11

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.6644. Min Act: -0.1700

Data Index: 1589828 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.6957. Min Act: -0.1700

Data Index: 832133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7583. Min Act: -0.1700

Data Index: 1546987 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7270. Min Act: -0.1700

Data Index: 1454790 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7270. Min Act: -0.1700

Data Index: 1544206 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7270. Min Act: -0.1700

Data Index: 1588891 (Python Code)

Max Activating Token Index: 747

Text #17

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7270. Min Act: -0.1700

Data Index: 1119462 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.7270. Min Act: -0.1700

Data Index: 498249 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 3.9459. Min Range: -3.9459

Max Act: 3.6957. Min Act: -0.1700

Data Index: 634433 (C4 (Web Text))

Max Activating Token Index: 1023