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

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

Neuron 391 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: 3.3266. Min Range: -3.3266

Max Act: 3.3266. Min Act: -0.1700

Data Index: 573434 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2638. Min Act: -0.1700

Data Index: 1042367 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2166. Min Act: -0.1700

Data Index: 793557 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2009. Min Act: -0.1700

Data Index: 745968 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.2009. Min Act: -0.1700

Data Index: 441527 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1851. Min Act: -0.1700

Data Index: 307664 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1537. Min Act: -0.1700

Data Index: 642607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1379. Min Act: -0.1700

Data Index: 276644 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1379. Min Act: -0.1700

Data Index: 134988 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.1064. Min Act: -0.1700

Data Index: 454966 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0748. Min Act: -0.1700

Data Index: 752650 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0906. Min Act: -0.1700

Data Index: 657923 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0906. Min Act: -0.1700

Data Index: 1095654 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0906. Min Act: -0.1700

Data Index: 806055 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0748. Min Act: -0.1700

Data Index: 1124572 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0748. Min Act: -0.1700

Data Index: 728045 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0591. Min Act: -0.1700

Data Index: 772181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0748. Min Act: -0.1700

Data Index: 195935 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0433. Min Act: -0.1700

Data Index: 525155 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 3.3266. Min Range: -3.3266

Max Act: 3.0433. Min Act: -0.1700

Data Index: 596596 (C4 (Web Text))

Max Activating Token Index: 1023