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

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

Neuron 551 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.2267. Min Act: -0.1700

Data Index: 239948 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.1008. Min Act: -0.1700

Data Index: 629056 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0534. Min Act: -0.1700

Data Index: 465164 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9586. Min Act: -0.1700

Data Index: 53764 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.2267. Min Range: -3.2267

Max Act: 3.0061. Min Act: -0.1700

Data Index: 909260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9903. Min Act: -0.1700

Data Index: 118477 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9744. Min Act: -0.1700

Data Index: 871968 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9744. Min Act: -0.1700

Data Index: 1353824 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9428. Min Act: -0.1700

Data Index: 486642 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9269. Min Act: -0.1700

Data Index: 382131 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8952. Min Act: -0.1700

Data Index: 841157 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9111. Min Act: -0.1700

Data Index: 315826 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.9111. Min Act: -0.1700

Data Index: 441606 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8952. Min Act: -0.1700

Data Index: 1300299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8952. Min Act: -0.1700

Data Index: 722692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8952. Min Act: -0.1700

Data Index: 298557 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8952. Min Act: -0.1700

Data Index: 78246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8793. Min Act: -0.1700

Data Index: 75625 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8952. Min Act: -0.1700

Data Index: 188045 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.2267. Min Range: -3.2267

Max Act: 2.8952. Min Act: -0.1700

Data Index: 23852 (C4 (Web Text))

Max Activating Token Index: 1023