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

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

Neuron 146 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: 3.2728. Min Range: -3.2728

Max Act: 3.2728. Min Act: -0.1700

Data Index: 350042 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.2100. Min Act: -0.1700

Data Index: 1310336 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.1942. Min Act: -0.1700

Data Index: 753478 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.1470. Min Act: -0.1700

Data Index: 471066 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.1313. Min Act: -0.1700

Data Index: 1286319 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.1313. Min Act: -0.1700

Data Index: 1256820 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.1155. Min Act: -0.1700

Data Index: 738985 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.1155. Min Act: -0.1700

Data Index: 66592 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0997. Min Act: -0.1700

Data Index: 64070 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.1155. Min Act: -0.1700

Data Index: 1132309 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0840. Min Act: -0.1700

Data Index: 594608 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0366. Min Act: -0.1700

Data Index: 1069643 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0366. Min Act: -0.1700

Data Index: 904794 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0524. Min Act: -0.1700

Data Index: 203455 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0366. Min Act: -0.1700

Data Index: 585558 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0366. Min Act: -0.1700

Data Index: 303596 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0524. Min Act: -0.1700

Data Index: 837589 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0682. Min Act: -0.1700

Data Index: 72429 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0366. Min Act: -0.1700

Data Index: 137861 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 3.2728. Min Range: -3.2728

Max Act: 3.0050. Min Act: -0.1700

Data Index: 331467 (C4 (Web Text))

Max Activating Token Index: 822