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

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

Neuron 1268 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: 3.5077. Min Range: -3.5077

Max Act: 3.5077. Min Act: -0.1700

Data Index: 370857 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.5077. Min Act: -0.1700

Data Index: 1036641 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.4763. Min Act: -0.1700

Data Index: 810338 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.4607. Min Act: -0.1700

Data Index: 291179 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3979. Min Act: -0.1700

Data Index: 212952 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3979. Min Act: -0.1700

Data Index: 34022 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.4293. Min Act: -0.1700

Data Index: 1177979 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.4450. Min Act: -0.1700

Data Index: 186262 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3352. Min Act: -0.1700

Data Index: 584960 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3509. Min Act: -0.1700

Data Index: 170793 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3823. Min Act: -0.1700

Data Index: 359742 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3979. Min Act: -0.1700

Data Index: 556617 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3666. Min Act: -0.1700

Data Index: 497853 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3979. Min Act: -0.1700

Data Index: 450803 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3666. Min Act: -0.1700

Data Index: 1195050 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3823. Min Act: -0.1700

Data Index: 424897 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3823. Min Act: -0.1700

Data Index: 37487 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3195. Min Act: -0.1700

Data Index: 1246873 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3509. Min Act: -0.1700

Data Index: 880476 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 3.5077. Min Range: -3.5077

Max Act: 3.3509. Min Act: -0.1700

Data Index: 138859 (C4 (Web Text))

Max Activating Token Index: 845