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

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

Neuron 1887 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5894. Min Act: -0.1700

Data Index: 967599 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5894. Min Act: -0.1700

Data Index: 1049201 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5737. Min Act: -0.1700

Data Index: 382240 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5580. Min Act: -0.1700

Data Index: 801079 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5580. Min Act: -0.1700

Data Index: 61650 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5267. Min Act: -0.1700

Data Index: 645722 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5424. Min Act: -0.1700

Data Index: 461851 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5267. Min Act: -0.1700

Data Index: 1118500 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5110. Min Act: -0.1700

Data Index: 75044 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5267. Min Act: -0.1700

Data Index: 204737 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5267. Min Act: -0.1700

Data Index: 1044507 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5267. Min Act: -0.1700

Data Index: 898416 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5110. Min Act: -0.1700

Data Index: 1130470 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5267. Min Act: -0.1700

Data Index: 108948 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4954. Min Act: -0.1700

Data Index: 979343 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.5110. Min Act: -0.1700

Data Index: 119490 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4640. Min Act: -0.1700

Data Index: 392564 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4954. Min Act: -0.1700

Data Index: 1061746 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4797. Min Act: -0.1700

Data Index: 267645 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 3.5894. Min Range: -3.5894

Max Act: 3.4797. Min Act: -0.1700

Data Index: 696125 (C4 (Web Text))

Max Activating Token Index: 787