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

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

Neuron 997 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: 3.9689. Min Range: -3.9689

Max Act: 3.9689. Min Act: -0.1700

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.9689. Min Act: -0.1700

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.9064. Min Act: -0.1700

Data Index: 396684 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1318616 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.8751. Min Act: -0.1700

Data Index: 1085673 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.8438. Min Act: -0.1700

Data Index: 372335 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.8438. Min Act: -0.1700

Data Index: 1282089 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.8125. Min Act: -0.1700

Data Index: 339952 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.7500. Min Act: -0.1700

Data Index: 168811 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.7187. Min Act: -0.1700

Data Index: 1348743 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.7812. Min Act: -0.1700

Data Index: 709059 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6874. Min Act: -0.1700

Data Index: 404279 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6874. Min Act: -0.1700

Data Index: 413227 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6874. Min Act: -0.1700

Data Index: 934563 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6874. Min Act: -0.1700

Data Index: 1179162 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6248. Min Act: -0.1700

Data Index: 934806 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6561. Min Act: -0.1700

Data Index: 412487 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6561. Min Act: -0.1700

Data Index: 147142 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6561. Min Act: -0.1700

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 3.9689. Min Range: -3.9689

Max Act: 3.6874. Min Act: -0.1700

Data Index: 940240 (C4 (Web Text))

Max Activating Token Index: 20