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

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

Neuron 1522 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.8637. Min Act: -0.1700

Data Index: 745160 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.6137. Min Act: -0.1700

Data Index: 625814 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.5824. Min Act: -0.1700

Data Index: 719865 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.4887. Min Act: -0.1700

Data Index: 1389736 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.4887. Min Act: -0.1700

Data Index: 1169 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.4574. Min Act: -0.1700

Data Index: 846953 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.3949. Min Act: -0.1698

Data Index: 984752 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.4574. Min Act: -0.1700

Data Index: 842027 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.4262. Min Act: -0.1700

Data Index: 541659 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.3949. Min Act: -0.1700

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.3949. Min Act: -0.1700

Data Index: 307934 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.3637. Min Act: -0.1700

Data Index: 73886 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.3012. Min Act: -0.1700

Data Index: 54116 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.3012. Min Act: -0.1700

Data Index: 684861 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.3012. Min Act: -0.1700

Data Index: 1339960 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.2699. Min Act: -0.1700

Data Index: 310919 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.2699. Min Act: -0.1700

Data Index: 782445 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.2387. Min Act: -0.1700

Data Index: 433868 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.2074. Min Act: -0.1700

Data Index: 675981 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 5.8637. Min Range: -5.8637

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1283435 (C4 (Web Text))

Max Activating Token Index: 912