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

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

Neuron 368 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: 3.5832. Min Range: -3.5832

Max Act: 3.5675. Min Act: -0.1700

Data Index: 84356 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.5518. Min Act: -0.1700

Data Index: 675922 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.5832. Min Act: -0.1700

Data Index: 1265988 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.5832. Min Act: -0.1700

Data Index: 1163964 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.5205. Min Act: -0.1700

Data Index: 122661 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.5675. Min Act: -0.1700

Data Index: 420557 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4578. Min Act: -0.1700

Data Index: 1200596 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4735. Min Act: -0.1700

Data Index: 221366 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4892. Min Act: -0.1700

Data Index: 589909 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4265. Min Act: -0.1700

Data Index: 904171 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4265. Min Act: -0.1700

Data Index: 1243253 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.3794. Min Act: -0.1700

Data Index: 658976 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4108. Min Act: -0.1700

Data Index: 314016 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4108. Min Act: -0.1700

Data Index: 654112 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.3951. Min Act: -0.1700

Data Index: 1224347 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.3951. Min Act: -0.1700

Data Index: 231115 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.4265. Min Act: -0.1700

Data Index: 63562 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.3637. Min Act: -0.1700

Data Index: 665192 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.3637. Min Act: -0.1700

Data Index: 453061 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 3.5832. Min Range: -3.5832

Max Act: 3.3637. Min Act: -0.1700

Data Index: 563239 (C4 (Web Text))

Max Activating Token Index: 188