Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1410 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.1415. Min Act: -0.1700

Data Index: 360478 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.1100. Min Act: -0.1700

Data Index: 522624 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0785. Min Act: -0.1700

Data Index: 1169671 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0627. Min Act: -0.1700

Data Index: 1136131 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0627. Min Act: -0.1700

Data Index: 582648 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1012549 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0311. Min Act: -0.1700

Data Index: 1206679 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0311. Min Act: -0.1700

Data Index: 940454 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1126726 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0469. Min Act: -0.1700

Data Index: 65908 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0469. Min Act: -0.1700

Data Index: 383166 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0311. Min Act: -0.1700

Data Index: 358434 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0311. Min Act: -0.1700

Data Index: 323393 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0311. Min Act: -0.1700

Data Index: 422919 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0153. Min Act: -0.1700

Data Index: 643260 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0153. Min Act: -0.1700

Data Index: 507736 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0311. Min Act: -0.1700

Data Index: 1182869 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 3.1415. Min Range: -3.1415

Max Act: 2.9995. Min Act: -0.1700

Data Index: 1003036 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0153. Min Act: -0.1700

Data Index: 834916 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 3.1415. Min Range: -3.1415

Max Act: 3.0153. Min Act: -0.1700

Data Index: 1026681 (C4 (Web Text))

Max Activating Token Index: 649