Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 962 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.7877. Min Act: -0.1700

Data Index: 685758 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.5999. Min Act: -0.1700

Data Index: 643162 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4902. Min Act: -0.1700

Data Index: 304663 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.5059. Min Act: -0.1700

Data Index: 180049 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4902. Min Act: -0.1700

Data Index: 588458 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4746. Min Act: -0.1700

Data Index: 374740 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4902. Min Act: -0.1700

Data Index: 245693 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4746. Min Act: -0.1700

Data Index: 999960 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4589. Min Act: -0.1700

Data Index: 960366 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4432. Min Act: -0.1700

Data Index: 1057271 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4432. Min Act: -0.1700

Data Index: 600980 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4589. Min Act: -0.1700

Data Index: 476266 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4432. Min Act: -0.1700

Data Index: 571372 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4432. Min Act: -0.1700

Data Index: 350014 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4432. Min Act: -0.1700

Data Index: 548628 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4746. Min Act: -0.1700

Data Index: 423870 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4589. Min Act: -0.1700

Data Index: 672700 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4589. Min Act: -0.1700

Data Index: 444265 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4432. Min Act: -0.1700

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 3.7877. Min Range: -3.7877

Max Act: 3.4275. Min Act: -0.1700

Data Index: 504527 (C4 (Web Text))

Max Activating Token Index: 991