Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1324 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.7882. Min Act: -0.1700

Data Index: 668698 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.7569. Min Act: -0.1700

Data Index: 787229 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6631. Min Act: -0.1700

Data Index: 452681 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6631. Min Act: -0.1700

Data Index: 1125285 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6944. Min Act: -0.1700

Data Index: 1056421 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6631. Min Act: -0.1700

Data Index: 36961 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6944. Min Act: -0.1700

Data Index: 916746 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6631. Min Act: -0.1700

Data Index: 368362 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6631. Min Act: -0.1700

Data Index: 1132355 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6318. Min Act: -0.1700

Data Index: 1472536 (Python Code)

Max Activating Token Index: 262

Text #10

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6318. Min Act: -0.1700

Data Index: 349094 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6004. Min Act: -0.1700

Data Index: 933748 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6318. Min Act: -0.1700

Data Index: 279572 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.5848. Min Act: -0.1700

Data Index: 1029266 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6004. Min Act: -0.1700

Data Index: 960101 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6004. Min Act: -0.1700

Data Index: 512174 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6004. Min Act: -0.1700

Data Index: 1202036 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.5848. Min Act: -0.1700

Data Index: 458226 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6004. Min Act: -0.1700

Data Index: 30626 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 3.7882. Min Range: -3.7882

Max Act: 3.6004. Min Act: -0.1700

Data Index: 995489 (C4 (Web Text))

Max Activating Token Index: 190