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

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

Neuron 1791 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: 4.1365. Min Range: -4.1365

Max Act: 4.1365. Min Act: -0.1700

Data Index: 1132065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.1365. Min Range: -4.1365

Max Act: 4.1053. Min Act: -0.1700

Data Index: 799425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.9489. Min Act: -0.1700

Data Index: 1232831 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.8864. Min Act: -0.1700

Data Index: 669734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.7926. Min Act: -0.1700

Data Index: 1229753 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.7613. Min Act: -0.1700

Data Index: 798527 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.7613. Min Act: -0.1700

Data Index: 1275087 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.7300. Min Act: -0.1700

Data Index: 821749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.7300. Min Act: -0.1700

Data Index: 938391 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6987. Min Act: -0.1700

Data Index: 660380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6987. Min Act: -0.1700

Data Index: 768604 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6987. Min Act: -0.1700

Data Index: 650082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6987. Min Act: -0.1700

Data Index: 313682 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6674. Min Act: -0.1700

Data Index: 981257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6048. Min Act: -0.1700

Data Index: 677025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6048. Min Act: -0.1700

Data Index: 784575 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.6048. Min Act: -0.1699

Data Index: 127930 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.5735. Min Act: -0.1700

Data Index: 4522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.5735. Min Act: -0.1700

Data Index: 935992 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.1365. Min Range: -4.1365

Max Act: 3.5735. Min Act: -0.1700

Data Index: 380568 (C4 (Web Text))

Max Activating Token Index: 1023