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

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

Neuron 1880 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: 3.7027. Min Range: -3.7027

Max Act: 3.7027. Min Act: -0.1700

Data Index: 210751 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.6714. Min Act: -0.1700

Data Index: 1215197 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.5462. Min Act: -0.1700

Data Index: 511304 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.5775. Min Act: -0.1700

Data Index: 1276226 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.5149. Min Act: -0.1700

Data Index: 1019307 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4208. Min Act: -0.1700

Data Index: 357990 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.5149. Min Act: -0.1700

Data Index: 794102 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4835. Min Act: -0.1700

Data Index: 1026320 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4522. Min Act: -0.1700

Data Index: 32497 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4522. Min Act: -0.1700

Data Index: 797118 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4522. Min Act: -0.1700

Data Index: 306902 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4208. Min Act: -0.1700

Data Index: 1260633 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4208. Min Act: -0.1700

Data Index: 260405 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4208. Min Act: -0.1700

Data Index: 975925 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4208. Min Act: -0.1700

Data Index: 764890 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.3894. Min Act: -0.1700

Data Index: 914830 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4208. Min Act: -0.1700

Data Index: 1250660 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.3894. Min Act: -0.1700

Data Index: 542055 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.4208. Min Act: -0.1700

Data Index: 991220 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.7027. Min Range: -3.7027

Max Act: 3.3894. Min Act: -0.1700

Data Index: 535432 (C4 (Web Text))

Max Activating Token Index: 740