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

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

Neuron 245 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: 4.4824. Min Range: -4.4824

Max Act: 4.4824. Min Act: -0.1700

Data Index: 743462 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.4199. Min Act: -0.1700

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.2324. Min Act: -0.1700

Data Index: 105157 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.2636. Min Act: -0.1700

Data Index: 193882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.2324. Min Act: -0.1700

Data Index: 1129615 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.2011. Min Act: -0.1700

Data Index: 612345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.1386. Min Act: -0.1700

Data Index: 140938 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.2011. Min Act: -0.1700

Data Index: 477430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.1073. Min Act: -0.1700

Data Index: 992919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0761. Min Act: -0.1700

Data Index: 412952 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.1073. Min Act: -0.1700

Data Index: 901538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.1073. Min Act: -0.1700

Data Index: 1287569 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0761. Min Act: -0.1700

Data Index: 684926 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.1073. Min Act: -0.1700

Data Index: 1045246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0448. Min Act: -0.1700

Data Index: 772112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0448. Min Act: -0.1700

Data Index: 818430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0136. Min Act: -0.1700

Data Index: 1066721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0448. Min Act: -0.1700

Data Index: 532511 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0136. Min Act: -0.1700

Data Index: 804081 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.4824. Min Range: -4.4824

Max Act: 4.0136. Min Act: -0.1700

Data Index: 821521 (C4 (Web Text))

Max Activating Token Index: 1023