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

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

Neuron 1496 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0683. Min Range: -3.0683

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1110662 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.0683. Min Range: -3.0683

Max Act: 3.0051. Min Act: -0.1700

Data Index: 1218364 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.9260. Min Act: -0.1700

Data Index: 851541 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.8467. Min Act: -0.1700

Data Index: 106409 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.8308. Min Act: -0.1700

Data Index: 738621 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.8308. Min Act: -0.1700

Data Index: 878204 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.8148. Min Act: -0.1700

Data Index: 1207564 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.8148. Min Act: -0.1700

Data Index: 855918 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.8308. Min Act: -0.1700

Data Index: 16299 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7989. Min Act: -0.1700

Data Index: 575106 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7989. Min Act: -0.1700

Data Index: 880003 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7989. Min Act: -0.1700

Data Index: 981540 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7830. Min Act: -0.1700

Data Index: 844504 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7830. Min Act: -0.1700

Data Index: 979714 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7830. Min Act: -0.1700

Data Index: 539951 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7830. Min Act: -0.1700

Data Index: 402367 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7989. Min Act: -0.1700

Data Index: 367570 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7670. Min Act: -0.1700

Data Index: 1166762 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7511. Min Act: -0.1700

Data Index: 1208138 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 3.0683. Min Range: -3.0683

Max Act: 2.7830. Min Act: -0.1700

Data Index: 483216 (C4 (Web Text))

Max Activating Token Index: 218