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

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

Neuron 908 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: 3.9460. Min Range: -3.9460

Max Act: 3.9460. Min Act: -0.1700

Data Index: 319080 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.7270. Min Act: -0.1700

Data Index: 435863 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.6644. Min Act: -0.1700

Data Index: 1150011 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5392. Min Act: -0.1700

Data Index: 796401 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5392. Min Act: -0.1700

Data Index: 1048415 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.6018. Min Act: -0.1700

Data Index: 937347 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5392. Min Act: -0.1700

Data Index: 998525 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5392. Min Act: -0.1700

Data Index: 257515 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5078. Min Act: -0.1700

Data Index: 1227304 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5392. Min Act: -0.1700

Data Index: 1142880 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.6018. Min Act: -0.1700

Data Index: 972914 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5078. Min Act: -0.1700

Data Index: 639263 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.4765. Min Act: -0.1700

Data Index: 530457 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5392. Min Act: -0.1700

Data Index: 781430 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.4765. Min Act: -0.1700

Data Index: 374699 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.4451. Min Act: -0.1700

Data Index: 1005687 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5078. Min Act: -0.1700

Data Index: 1055224 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.5392. Min Act: -0.1699

Data Index: 854923 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.3824. Min Act: -0.1700

Data Index: 752348 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 3.9460. Min Range: -3.9460

Max Act: 3.4138. Min Act: -0.1700

Data Index: 257298 (C4 (Web Text))

Max Activating Token Index: 514