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

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

Neuron 1837 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.8411. Min Act: -0.1700

Data Index: 724181 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.8099. Min Act: -0.1700

Data Index: 1051819 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.8411. Min Act: -0.1700

Data Index: 1089144 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.6534. Min Act: -0.1700

Data Index: 914958 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.6847. Min Act: -0.1700

Data Index: 402412 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.6534. Min Act: -0.1700

Data Index: 766932 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.6534. Min Act: -0.1700

Data Index: 496638 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.5908. Min Act: -0.1700

Data Index: 1110365 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.5751. Min Act: -0.1700

Data Index: 573954 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.5125. Min Act: -0.1700

Data Index: 269108 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.4811. Min Act: -0.1700

Data Index: 885890 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.4341. Min Act: -0.1700

Data Index: 405863 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.4498. Min Act: -0.1700

Data Index: 1151814 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.4027. Min Act: -0.1700

Data Index: 672503 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.4341. Min Act: -0.1700

Data Index: 140035 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.3871. Min Act: -0.1700

Data Index: 545086 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.3871. Min Act: -0.1700

Data Index: 203854 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.4027. Min Act: -0.1700

Data Index: 427300 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.3871. Min Act: -0.1700

Data Index: 60402 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.3871. Min Act: -0.1700

Data Index: 964864 (C4 (Web Text))

Max Activating Token Index: 560