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

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

Neuron 1833 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: 5.6973. Min Range: -5.6973

Max Act: 5.6035. Min Act: -0.1700

Data Index: 854705 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.6660. Min Act: -0.1700

Data Index: 186168 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.6973. Min Act: -0.1700

Data Index: 636196 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.6035. Min Act: -0.1700

Data Index: 1020775 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5410. Min Act: -0.1700

Data Index: 236644 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5410. Min Act: -0.1700

Data Index: 351848 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5098. Min Act: -0.1700

Data Index: 293346 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5410. Min Act: -0.1700

Data Index: 1131388 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.4785. Min Act: -0.1700

Data Index: 778580 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5098. Min Act: -0.1700

Data Index: 1111935 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5098. Min Act: -0.1700

Data Index: 845865 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5098. Min Act: -0.1700

Data Index: 636741 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.4785. Min Act: -0.1700

Data Index: 440938 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.4785. Min Act: -0.1700

Data Index: 602019 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5098. Min Act: -0.1700

Data Index: 26820 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5098. Min Act: -0.1700

Data Index: 99677 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.5098. Min Act: -0.1700

Data Index: 882542 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.4785. Min Act: -0.1700

Data Index: 104971 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.4160. Min Act: -0.1700

Data Index: 629085 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 5.6973. Min Range: -5.6973

Max Act: 5.4160. Min Act: -0.1700

Data Index: 541335 (C4 (Web Text))

Max Activating Token Index: 656