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

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

Neuron 459 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: 3.9799. Min Range: -3.9799

Max Act: 3.9799. Min Act: -0.1700

Data Index: 830577 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.9799. Min Act: -0.1700

Data Index: 971199 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.8861. Min Act: -0.1700

Data Index: 1301174 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.8861. Min Act: -0.1700

Data Index: 293099 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.8548. Min Act: -0.1700

Data Index: 1525383 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7610. Min Act: -0.1700

Data Index: 419132 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.8548. Min Act: -0.1700

Data Index: 837034 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7922. Min Act: -0.1700

Data Index: 787271 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7922. Min Act: -0.1700

Data Index: 530306 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.8548. Min Act: -0.1700

Data Index: 1229029 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7922. Min Act: -0.1700

Data Index: 1264893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7297. Min Act: -0.1700

Data Index: 173216 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7922. Min Act: -0.1700

Data Index: 1101086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7922. Min Act: -0.1700

Data Index: 1054293 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.8235. Min Act: -0.1700

Data Index: 895912 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7610. Min Act: -0.1700

Data Index: 108768 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6984. Min Act: -0.1700

Data Index: 209425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6045. Min Act: -0.1700

Data Index: 978200 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6671. Min Act: -0.1700

Data Index: 900990 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6671. Min Act: -0.1700

Data Index: 283667 (C4 (Web Text))

Max Activating Token Index: 125