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

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

Neuron 531 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: 3.2710. Min Range: -3.2710

Max Act: 3.2710. Min Act: -0.1700

Data Index: 981141 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.1452. Min Act: -0.1700

Data Index: 420294 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.1294. Min Act: -0.1700

Data Index: 18314 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.0979. Min Act: -0.1700

Data Index: 990154 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.0506. Min Act: -0.1700

Data Index: 163553 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.0032. Min Act: -0.1700

Data Index: 155802 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.0032. Min Act: -0.1700

Data Index: 1048788 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.2710. Min Range: -3.2710

Max Act: 3.0032. Min Act: -0.1700

Data Index: 801900 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.9715. Min Act: -0.1700

Data Index: 1086042 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.9557. Min Act: -0.1700

Data Index: 1141825 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.9557. Min Act: -0.1700

Data Index: 1261866 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8923. Min Act: -0.1700

Data Index: 1262603 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.9240. Min Act: -0.1700

Data Index: 369204 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.9399. Min Act: -0.1700

Data Index: 107136 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8923. Min Act: -0.1700

Data Index: 395214 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8923. Min Act: -0.1700

Data Index: 410027 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8447. Min Act: -0.1700

Data Index: 420787 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1347281 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8606. Min Act: -0.1700

Data Index: 801285 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.2710. Min Range: -3.2710

Max Act: 2.8606. Min Act: -0.1700

Data Index: 56609 (C4 (Web Text))

Max Activating Token Index: 577