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

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

Neuron 1921 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0972. Min Range: -5.0972

Max Act: 5.0972. Min Act: -0.1700

Data Index: 1059678 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 5.0972. Min Range: -5.0972

Max Act: 5.0035. Min Act: -0.1700

Data Index: 1288347 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 5.0972. Min Range: -5.0972

Max Act: 5.0347. Min Act: -0.1700

Data Index: 1248598 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 5.0972. Min Range: -5.0972

Max Act: 5.0660. Min Act: -0.1700

Data Index: 842218 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9722. Min Act: -0.1700

Data Index: 659970 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 5.0972. Min Range: -5.0972

Max Act: 5.0035. Min Act: -0.1700

Data Index: 1088773 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 5.0972. Min Range: -5.0972

Max Act: 5.0035. Min Act: -0.1700

Data Index: 898671 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 5.0972. Min Range: -5.0972

Max Act: 5.0035. Min Act: -0.1700

Data Index: 1312189 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9722. Min Act: -0.1700

Data Index: 554363 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9722. Min Act: -0.1700

Data Index: 58321 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9410. Min Act: -0.1700

Data Index: 694285 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9410. Min Act: -0.1700

Data Index: 22751 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9097. Min Act: -0.1700

Data Index: 1074924 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9410. Min Act: -0.1700

Data Index: 512286 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.8785. Min Act: -0.1700

Data Index: 314401 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9097. Min Act: -0.1700

Data Index: 121947 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9410. Min Act: -0.1700

Data Index: 1053446 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9097. Min Act: -0.1700

Data Index: 437838 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.9410. Min Act: -0.1700

Data Index: 545261 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 5.0972. Min Range: -5.0972

Max Act: 4.8785. Min Act: -0.1700

Data Index: 133976 (C4 (Web Text))

Max Activating Token Index: 188