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

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

Neuron 601 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1673. Min Range: -5.1673

Max Act: 5.1673. Min Act: -0.1700

Data Index: 668682 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8392. Min Act: -0.1700

Data Index: 454800 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.9330. Min Act: -0.1700

Data Index: 800915 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.9486. Min Act: -0.1700

Data Index: 113011 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 5.1673. Min Range: -5.1673

Max Act: 5.0111. Min Act: -0.1700

Data Index: 1260188 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.9017. Min Act: -0.1700

Data Index: 1059022 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8861. Min Act: -0.1700

Data Index: 162160 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.7923. Min Act: -0.1700

Data Index: 962225 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.9173. Min Act: -0.1700

Data Index: 560618 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8236. Min Act: -0.1700

Data Index: 205680 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.9017. Min Act: -0.1700

Data Index: 773181 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.9017. Min Act: -0.1700

Data Index: 1154967 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8548. Min Act: -0.1700

Data Index: 1312844 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.9017. Min Act: -0.1700

Data Index: 995316 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8548. Min Act: -0.1700

Data Index: 33038 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8548. Min Act: -0.1700

Data Index: 1100027 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8080. Min Act: -0.1700

Data Index: 1043468 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.7455. Min Act: -0.1700

Data Index: 842281 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.7923. Min Act: -0.1700

Data Index: 206775 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 5.1673. Min Range: -5.1673

Max Act: 4.8080. Min Act: -0.1700

Data Index: 132151 (C4 (Web Text))

Max Activating Token Index: 431