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

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

Neuron 382 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: 4.1346. Min Range: -4.1346

Max Act: 4.1346. Min Act: -0.1700

Data Index: 215194 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.1346. Min Range: -4.1346

Max Act: 4.0096. Min Act: -0.1700

Data Index: 162655 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.9783. Min Act: -0.1700

Data Index: 650908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8845. Min Act: -0.1700

Data Index: 355001 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8845. Min Act: -0.1700

Data Index: 91481 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8845. Min Act: -0.1700

Data Index: 945316 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8532. Min Act: -0.1700

Data Index: 17736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8532. Min Act: -0.1700

Data Index: 1182962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8220. Min Act: -0.1700

Data Index: 454849 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8220. Min Act: -0.1700

Data Index: 938924 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7907. Min Act: -0.1700

Data Index: 283171 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.8220. Min Act: -0.1700

Data Index: 373423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7907. Min Act: -0.1700

Data Index: 975938 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7907. Min Act: -0.1700

Data Index: 973192 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7594. Min Act: -0.1700

Data Index: 528434 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7594. Min Act: -0.1700

Data Index: 1013705 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7281. Min Act: -0.1700

Data Index: 933798 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7594. Min Act: -0.1700

Data Index: 761837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.7281. Min Act: -0.1700

Data Index: 992855 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.1346. Min Range: -4.1346

Max Act: 3.6968. Min Act: -0.1700

Data Index: 575620 (C4 (Web Text))

Max Activating Token Index: 1023