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

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

Neuron 702 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: 5.5187. Min Range: -5.5187

Max Act: 5.5187. Min Act: -0.1700

Data Index: 393262 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.5187. Min Range: -5.5187

Max Act: 5.1125. Min Act: -0.1700

Data Index: 44998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.5187. Min Range: -5.5187

Max Act: 5.0500. Min Act: -0.1700

Data Index: 922593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9875. Min Act: -0.1700

Data Index: 1328680 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9250. Min Act: -0.1700

Data Index: 1031967 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9875. Min Act: -0.1700

Data Index: 1250610 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.8312. Min Act: -0.1700

Data Index: 1622982 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.8937. Min Act: -0.1700

Data Index: 777367 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9250. Min Act: -0.1700

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9562. Min Act: -0.1700

Data Index: 713622 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9250. Min Act: -0.1700

Data Index: 883162 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9562. Min Act: -0.1700

Data Index: 1204497 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.8312. Min Act: -0.1700

Data Index: 859812 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9875. Min Act: -0.1700

Data Index: 1199381 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9250. Min Act: -0.1700

Data Index: 1177152 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.9250. Min Act: -0.1700

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.8937. Min Act: -0.1700

Data Index: 924144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.8625. Min Act: -0.1700

Data Index: 243864 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.8312. Min Act: -0.1700

Data Index: 917223 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 5.5187. Min Range: -5.5187

Max Act: 4.7375. Min Act: -0.1700

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 861