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

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

Neuron 1522 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: 5.2859. Min Range: -5.2859

Max Act: 5.2859. Min Act: -0.1700

Data Index: 618758 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.1297. Min Act: -0.1700

Data Index: 387262 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0984. Min Act: -0.1700

Data Index: 180255 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0672. Min Act: -0.1700

Data Index: 1343072 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0672. Min Act: -0.1700

Data Index: 75559 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0047. Min Act: -0.1700

Data Index: 570706 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0672. Min Act: -0.1700

Data Index: 623527 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0672. Min Act: -0.1700

Data Index: 1282171 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0672. Min Act: -0.1700

Data Index: 255921 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0359. Min Act: -0.1700

Data Index: 489838 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0047. Min Act: -0.1700

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 5.2859. Min Range: -5.2859

Max Act: 4.9734. Min Act: -0.1700

Data Index: 298026 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0047. Min Act: -0.1700

Data Index: 1342015 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0047. Min Act: -0.1700

Data Index: 230752 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 5.2859. Min Range: -5.2859

Max Act: 4.9109. Min Act: -0.1700

Data Index: 948089 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 5.2859. Min Range: -5.2859

Max Act: 4.9734. Min Act: -0.1700

Data Index: 57175 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 5.2859. Min Range: -5.2859

Max Act: 4.9422. Min Act: -0.1700

Data Index: 1004148 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 5.2859. Min Range: -5.2859

Max Act: 4.9734. Min Act: -0.1700

Data Index: 875837 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 5.2859. Min Range: -5.2859

Max Act: 5.0047. Min Act: -0.1700

Data Index: 640593 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 5.2859. Min Range: -5.2859

Max Act: 4.9109. Min Act: -0.1700

Data Index: 524105 (C4 (Web Text))

Max Activating Token Index: 918