Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1998 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0718. Min Range: -3.0718

Max Act: 3.0718. Min Act: -0.1700

Data Index: 1078562 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 3.0718. Min Range: -3.0718

Max Act: 3.0123. Min Act: -0.1700

Data Index: 1244357 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.0718. Min Range: -3.0718

Max Act: 3.0057. Min Act: -0.1700

Data Index: 921917 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.9913. Min Act: -0.1700

Data Index: 932891 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.9566. Min Act: -0.1700

Data Index: 1569411 (Python Code)

Max Activating Token Index: 498

Text #5

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.9345. Min Act: -0.1700

Data Index: 515461 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.9332. Min Act: -0.1700

Data Index: 929489 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.9112. Min Act: -0.1698

Data Index: 1004300 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.9077. Min Act: -0.1700

Data Index: 723058 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8994. Min Act: -0.1700

Data Index: 1026801 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.9039. Min Act: -0.1700

Data Index: 988286 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8909. Min Act: -0.1700

Data Index: 251246 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8891. Min Act: -0.1699

Data Index: 930918 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8829. Min Act: -0.1700

Data Index: 1046963 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8705. Min Act: -0.1699

Data Index: 1045069 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8695. Min Act: -0.1700

Data Index: 375659 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8715. Min Act: -0.1700

Data Index: 1042927 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8830. Min Act: -0.1700

Data Index: 237581 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8661. Min Act: -0.1700

Data Index: 12351 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 3.0718. Min Range: -3.0718

Max Act: 2.8466. Min Act: -0.1700

Data Index: 647441 (C4 (Web Text))

Max Activating Token Index: 398