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

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

Neuron 593 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: 3.7866. Min Range: -3.7866

Max Act: 3.7866. Min Act: -0.1700

Data Index: 929607 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7866. Min Act: -0.1700

Data Index: 950169 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7866. Min Act: -0.1700

Data Index: 782766 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7866. Min Act: -0.1700

Data Index: 185544 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6928. Min Act: -0.1700

Data Index: 344956 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6615. Min Act: -0.1700

Data Index: 1185159 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6615. Min Act: -0.1700

Data Index: 464504 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.7241. Min Act: -0.1700

Data Index: 108723 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6302. Min Act: -0.1700

Data Index: 840216 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6302. Min Act: -0.1700

Data Index: 996534 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6302. Min Act: -0.1700

Data Index: 843691 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6302. Min Act: -0.1700

Data Index: 850841 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6615. Min Act: -0.1700

Data Index: 499609 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6615. Min Act: -0.1700

Data Index: 1138708 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6302. Min Act: -0.1700

Data Index: 1067657 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.5989. Min Act: -0.1700

Data Index: 1063403 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.5989. Min Act: -0.1700

Data Index: 407766 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.6302. Min Act: -0.1700

Data Index: 550285 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.5362. Min Act: -0.1700

Data Index: 1026915 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 3.7866. Min Range: -3.7866

Max Act: 3.5362. Min Act: -0.1700

Data Index: 630417 (C4 (Web Text))

Max Activating Token Index: 355