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

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

Neuron 429 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: 3.4583. Min Range: -3.4583

Max Act: 3.4269. Min Act: -0.1700

Data Index: 607244 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.4269. Min Act: -0.1700

Data Index: 1404947 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.4269. Min Act: -0.1700

Data Index: 1178552 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.4583. Min Act: -0.1700

Data Index: 927183 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3642. Min Act: -0.1700

Data Index: 1244286 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 101497 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 204071 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 928629 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 742750 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3014. Min Act: -0.1700

Data Index: 1539646 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 1208597 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3014. Min Act: -0.1700

Data Index: 821369 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 142923 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3014. Min Act: -0.1700

Data Index: 312728 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 1343093 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3014. Min Act: -0.1700

Data Index: 863550 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3014. Min Act: -0.1700

Data Index: 255800 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.2700. Min Act: -0.1700

Data Index: 1157048 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3328. Min Act: -0.1700

Data Index: 146969 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.4583. Min Range: -3.4583

Max Act: 3.3014. Min Act: -0.1700

Data Index: 861447 (C4 (Web Text))

Max Activating Token Index: 896