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

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

Neuron 1796 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.4655. Min Act: -0.1700

Data Index: 488180 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.3405. Min Act: -0.1700

Data Index: 182567 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.2467. Min Act: -0.1700

Data Index: 354277 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.2155. Min Act: -0.1700

Data Index: 1328157 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1686. Min Act: -0.1700

Data Index: 1055512 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1842. Min Act: -0.1700

Data Index: 451109 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1686. Min Act: -0.1700

Data Index: 1063933 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1686. Min Act: -0.1700

Data Index: 867647 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1842. Min Act: -0.1700

Data Index: 633470 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1374. Min Act: -0.1700

Data Index: 1312395 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1530. Min Act: -0.1700

Data Index: 500090 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1842. Min Act: -0.1700

Data Index: 1001283 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1374. Min Act: -0.1700

Data Index: 1296491 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1217. Min Act: -0.1700

Data Index: 478851 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.1217. Min Act: -0.1700

Data Index: 287540 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.0905. Min Act: -0.1700

Data Index: 357323 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.0905. Min Act: -0.1700

Data Index: 315850 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.0592. Min Act: -0.1700

Data Index: 331998 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.0124. Min Act: -0.1700

Data Index: 190605 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 5.4655. Min Range: -5.4655

Max Act: 5.0592. Min Act: -0.1700

Data Index: 45825 (C4 (Web Text))

Max Activating Token Index: 635