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

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

Neuron 590 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: 3.4862. Min Range: -3.4862

Max Act: 3.4862. Min Act: -0.1700

Data Index: 907830 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4862. Min Act: -0.1700

Data Index: 106228 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4706. Min Act: -0.1700

Data Index: 1238876 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4549. Min Act: -0.1700

Data Index: 318566 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4549. Min Act: -0.1700

Data Index: 465531 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4549. Min Act: -0.1700

Data Index: 469133 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4392. Min Act: -0.1700

Data Index: 643462 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4392. Min Act: -0.1700

Data Index: 993771 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4392. Min Act: -0.1700

Data Index: 913033 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4235. Min Act: -0.1700

Data Index: 284207 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4235. Min Act: -0.1700

Data Index: 90011 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4235. Min Act: -0.1700

Data Index: 1303306 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4235. Min Act: -0.1700

Data Index: 114536 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4078. Min Act: -0.1700

Data Index: 545946 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.3922. Min Act: -0.1700

Data Index: 604176 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4078. Min Act: -0.1700

Data Index: 615231 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.3922. Min Act: -0.1700

Data Index: 157791 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.3922. Min Act: -0.1700

Data Index: 845435 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.4078. Min Act: -0.1700

Data Index: 1075413 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 3.4862. Min Range: -3.4862

Max Act: 3.3922. Min Act: -0.1700

Data Index: 535310 (C4 (Web Text))

Max Activating Token Index: 404