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

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

Neuron 1955 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6790. Min Act: -0.1700

Data Index: 695597 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6633. Min Act: -0.1700

Data Index: 260788 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6633. Min Act: -0.1700

Data Index: 797990 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6320. Min Act: -0.1700

Data Index: 497449 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6164. Min Act: -0.1700

Data Index: 1152706 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1309168 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1041268 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5537. Min Act: -0.1700

Data Index: 1023260 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1016071 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.6007. Min Act: -0.1700

Data Index: 502300 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1226891 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5224. Min Act: -0.1700

Data Index: 1172946 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1096539 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5694. Min Act: -0.1700

Data Index: 692555 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5381. Min Act: -0.1700

Data Index: 877831 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5694. Min Act: -0.1700

Data Index: 282123 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5381. Min Act: -0.1700

Data Index: 958133 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5537. Min Act: -0.1700

Data Index: 712459 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5224. Min Act: -0.1700

Data Index: 166918 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 3.6790. Min Range: -3.6790

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1089171 (C4 (Web Text))

Max Activating Token Index: 342