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

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

Neuron 933 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: 3.2628. Min Range: -3.2628

Max Act: 3.2628. Min Act: -0.1700

Data Index: 632890 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.2314. Min Act: -0.1700

Data Index: 450087 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1999. Min Act: -0.1700

Data Index: 16439 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1999. Min Act: -0.1700

Data Index: 984614 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1685. Min Act: -0.1700

Data Index: 730212 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1685. Min Act: -0.1700

Data Index: 300540 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1685. Min Act: -0.1700

Data Index: 357861 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1370. Min Act: -0.1700

Data Index: 1243725 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1999. Min Act: -0.1700

Data Index: 768567 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1685. Min Act: -0.1700

Data Index: 1008115 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1685. Min Act: -0.1700

Data Index: 88756 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1370. Min Act: -0.1700

Data Index: 1113616 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1055. Min Act: -0.1700

Data Index: 1254419 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1370. Min Act: -0.1700

Data Index: 232012 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1055. Min Act: -0.1700

Data Index: 588505 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1370. Min Act: -0.1700

Data Index: 1342700 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1055. Min Act: -0.1700

Data Index: 849266 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1055. Min Act: -0.1700

Data Index: 60813 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1055. Min Act: -0.1700

Data Index: 1267639 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1055. Min Act: -0.1700

Data Index: 236988 (C4 (Web Text))

Max Activating Token Index: 930