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

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

Neuron 287 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.4068. Min Act: -0.1700

Data Index: 769119 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.3443. Min Act: -0.1700

Data Index: 1281383 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.3755. Min Act: -0.1700

Data Index: 1309929 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.3755. Min Act: -0.1700

Data Index: 1220898 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.3130. Min Act: -0.1700

Data Index: 851414 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.3130. Min Act: -0.1700

Data Index: 1174555 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.2818. Min Act: -0.1700

Data Index: 901923 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.2505. Min Act: -0.1700

Data Index: 960216 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.2193. Min Act: -0.1700

Data Index: 1219152 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.2193. Min Act: -0.1700

Data Index: 875102 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.2193. Min Act: -0.1700

Data Index: 402988 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.1880. Min Act: -0.1700

Data Index: 1353313 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.2193. Min Act: -0.1700

Data Index: 1077554 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.1568. Min Act: -0.1700

Data Index: 930815 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.1880. Min Act: -0.1700

Data Index: 795162 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.1255. Min Act: -0.1700

Data Index: 1264375 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.1568. Min Act: -0.1700

Data Index: 450751 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.1568. Min Act: -0.1700

Data Index: 1221061 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.1568. Min Act: -0.1700

Data Index: 1039165 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 5.4068. Min Range: -5.4068

Max Act: 5.2505. Min Act: -0.1700

Data Index: 830618 (C4 (Web Text))

Max Activating Token Index: 959