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

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

Neuron 463 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: 3.6960. Min Range: -3.6960

Max Act: 3.6960. Min Act: -0.1700

Data Index: 706730 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6647. Min Act: -0.1700

Data Index: 1423 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6960. Min Act: -0.1700

Data Index: 1298159 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6647. Min Act: -0.1700

Data Index: 1128325 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 820915 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6647. Min Act: -0.1700

Data Index: 487002 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6647. Min Act: -0.1700

Data Index: 479078 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6647. Min Act: -0.1700

Data Index: 1093417 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 478851 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6647. Min Act: -0.1700

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 1555283 (Python Code)

Max Activating Token Index: 125

Text #11

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 150923 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6021. Min Act: -0.1700

Data Index: 1332173 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 630843 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 985888 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 1068285 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6647. Min Act: -0.1700

Data Index: 221246 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6334. Min Act: -0.1700

Data Index: 1301764 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 3.6960. Min Range: -3.6960

Max Act: 3.6021. Min Act: -0.1700

Data Index: 89898 (C4 (Web Text))

Max Activating Token Index: 229