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

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

Neuron 1599 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: 3.4929. Min Range: -3.4929

Max Act: 3.4302. Min Act: -0.1700

Data Index: 1234377 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.4929. Min Act: -0.1700

Data Index: 132168 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.4302. Min Act: -0.1700

Data Index: 982546 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.4302. Min Act: -0.1700

Data Index: 97111 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3674. Min Act: -0.1700

Data Index: 104006 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3674. Min Act: -0.1700

Data Index: 251906 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3361. Min Act: -0.1700

Data Index: 581061 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3361. Min Act: -0.1700

Data Index: 1060096 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3047. Min Act: -0.1700

Data Index: 833263 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3361. Min Act: -0.1700

Data Index: 43966 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3047. Min Act: -0.1700

Data Index: 811516 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3047. Min Act: -0.1700

Data Index: 1003987 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3047. Min Act: -0.1700

Data Index: 196901 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2732. Min Act: -0.1700

Data Index: 712805 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3047. Min Act: -0.1700

Data Index: 510650 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3047. Min Act: -0.1700

Data Index: 1295263 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3047. Min Act: -0.1700

Data Index: 158732 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2732. Min Act: -0.1700

Data Index: 905397 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2732. Min Act: -0.1700

Data Index: 393438 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2732. Min Act: -0.1700

Data Index: 172565 (C4 (Web Text))

Max Activating Token Index: 986