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

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

Neuron 863 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.5853. Min Act: -0.1700

Data Index: 315167 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.5383. Min Act: -0.1700

Data Index: 618621 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.5226. Min Act: -0.1700

Data Index: 1338840 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.5226. Min Act: -0.1700

Data Index: 1177396 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4913. Min Act: -0.1700

Data Index: 768670 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4756. Min Act: -0.1700

Data Index: 1585105 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4756. Min Act: -0.1700

Data Index: 396763 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4443. Min Act: -0.1700

Data Index: 1231217 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4286. Min Act: -0.1700

Data Index: 371267 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4129. Min Act: -0.1700

Data Index: 1002700 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4286. Min Act: -0.1700

Data Index: 439325 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4129. Min Act: -0.1700

Data Index: 773734 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4443. Min Act: -0.1700

Data Index: 1191802 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4129. Min Act: -0.1700

Data Index: 1420005 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.4129. Min Act: -0.1700

Data Index: 483389 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.3972. Min Act: -0.1700

Data Index: 679895 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.3972. Min Act: -0.1700

Data Index: 295700 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.3815. Min Act: -0.1700

Data Index: 985277 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.3815. Min Act: -0.1699

Data Index: 1226427 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 3.5853. Min Range: -3.5853

Max Act: 3.3658. Min Act: -0.1700

Data Index: 1642217 (Python Code)

Max Activating Token Index: 91