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

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

Neuron 616 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: 4.3080. Min Range: -4.3080

Max Act: 4.3080. Min Act: -0.1700

Data Index: 544905 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.2767. Min Act: -0.1700

Data Index: 358204 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.2142. Min Act: -0.1700

Data Index: 1065604 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.2142. Min Act: -0.1700

Data Index: 893851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.2142. Min Act: -0.1700

Data Index: 1188037 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.2142. Min Act: -0.1700

Data Index: 389155 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.1517. Min Act: -0.1700

Data Index: 51860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.1517. Min Act: -0.1700

Data Index: 1167414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.1517. Min Act: -0.1700

Data Index: 871575 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.1205. Min Act: -0.1700

Data Index: 415690 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.0892. Min Act: -0.1700

Data Index: 1027770 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.0579. Min Act: -0.1700

Data Index: 251953 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.0267. Min Act: -0.1700

Data Index: 304234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.0267. Min Act: -0.1700

Data Index: 1046058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.9954. Min Act: -0.1700

Data Index: 1105345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.9641. Min Act: -0.1700

Data Index: 762748 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.9954. Min Act: -0.1700

Data Index: 358135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.0267. Min Act: -0.1700

Data Index: 370790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.9954. Min Act: -0.1700

Data Index: 18398 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.9954. Min Act: -0.1700

Data Index: 801233 (C4 (Web Text))

Max Activating Token Index: 1023