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

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

Neuron 855 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.4060. Min Act: -0.1700

Data Index: 378144 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.1861. Min Act: -0.1700

Data Index: 910382 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.1704. Min Act: -0.1700

Data Index: 1166296 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.1546. Min Act: -0.1700

Data Index: 1018704 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.1389. Min Act: -0.1700

Data Index: 467334 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.1546. Min Act: -0.1700

Data Index: 629183 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.0758. Min Act: -0.1700

Data Index: 1090967 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.0284. Min Act: -0.1700

Data Index: 112855 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.0442. Min Act: -0.1700

Data Index: 1060589 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.0442. Min Act: -0.1700

Data Index: 830286 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 3.4060. Min Range: -3.4060

Max Act: 3.0126. Min Act: -0.1700

Data Index: 1190232 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9810. Min Act: -0.1700

Data Index: 413619 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9810. Min Act: -0.1700

Data Index: 350797 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9494. Min Act: -0.1700

Data Index: 132323 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9652. Min Act: -0.1700

Data Index: 662324 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9494. Min Act: -0.1700

Data Index: 744366 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9494. Min Act: -0.1700

Data Index: 809659 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9494. Min Act: -0.1700

Data Index: 860460 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9494. Min Act: -0.1700

Data Index: 40916 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 3.4060. Min Range: -3.4060

Max Act: 2.9494. Min Act: -0.1700

Data Index: 1312669 (C4 (Web Text))

Max Activating Token Index: 566