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

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

Neuron 1988 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3722. Min Act: -0.1700

Data Index: 1064966 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3408. Min Act: -0.1700

Data Index: 1295531 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2622. Min Act: -0.1700

Data Index: 1175518 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2465. Min Act: -0.1700

Data Index: 1035593 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2465. Min Act: -0.1700

Data Index: 720193 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2151. Min Act: -0.1700

Data Index: 802988 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2465. Min Act: -0.1700

Data Index: 408201 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2151. Min Act: -0.1700

Data Index: 860394 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2151. Min Act: -0.1700

Data Index: 334283 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1993. Min Act: -0.1700

Data Index: 199760 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2151. Min Act: -0.1700

Data Index: 501988 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2151. Min Act: -0.1700

Data Index: 308557 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1993. Min Act: -0.1700

Data Index: 158988 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1836. Min Act: -0.1700

Data Index: 839050 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1836. Min Act: -0.1700

Data Index: 1332500 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1836. Min Act: -0.1700

Data Index: 682294 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1521. Min Act: -0.1700

Data Index: 867616 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1679. Min Act: -0.1700

Data Index: 1053082 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1836. Min Act: -0.1700

Data Index: 268414 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.1521. Min Act: -0.1700

Data Index: 130436 (C4 (Web Text))

Max Activating Token Index: 264