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

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

Neuron 1649 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: 3.1930. Min Range: -3.1930

Max Act: 3.1930. Min Act: -0.1700

Data Index: 105102 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.1773. Min Act: -0.1700

Data Index: 574283 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.1615. Min Act: -0.1700

Data Index: 966507 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.1300. Min Act: -0.1700

Data Index: 669847 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.1143. Min Act: -0.1700

Data Index: 1233607 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0985. Min Act: -0.1700

Data Index: 1344254 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0985. Min Act: -0.1700

Data Index: 1253199 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0985. Min Act: -0.1700

Data Index: 1353543 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0827. Min Act: -0.1700

Data Index: 533179 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0827. Min Act: -0.1700

Data Index: 1163780 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0827. Min Act: -0.1700

Data Index: 286024 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0985. Min Act: -0.1700

Data Index: 24007 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0512. Min Act: -0.1700

Data Index: 838002 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0512. Min Act: -0.1700

Data Index: 313767 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0670. Min Act: -0.1700

Data Index: 423798 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0670. Min Act: -0.1700

Data Index: 513599 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0670. Min Act: -0.1700

Data Index: 1168709 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0512. Min Act: -0.1700

Data Index: 317385 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0670. Min Act: -0.1700

Data Index: 1247129 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 3.1930. Min Range: -3.1930

Max Act: 3.0670. Min Act: -0.1700

Data Index: 1274135 (C4 (Web Text))

Max Activating Token Index: 722