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

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

Neuron 63 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.1920. Min Act: -0.1700

Data Index: 1074603 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.1295. Min Act: -0.1700

Data Index: 458284 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0982. Min Act: -0.1700

Data Index: 600894 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9732. Min Act: -0.1700

Data Index: 158998 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0670. Min Act: -0.1700

Data Index: 700109 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9732. Min Act: -0.1700

Data Index: 55675 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0045. Min Act: -0.1700

Data Index: 434027 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0670. Min Act: -0.1700

Data Index: 896677 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0045. Min Act: -0.1700

Data Index: 1191784 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0982. Min Act: -0.1700

Data Index: 340550 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9107. Min Act: -0.1700

Data Index: 511082 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0045. Min Act: -0.1700

Data Index: 1238787 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0045. Min Act: -0.1699

Data Index: 573884 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 5.1920. Min Range: -5.1920

Max Act: 5.0357. Min Act: -0.1700

Data Index: 1201011 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9107. Min Act: -0.1700

Data Index: 639485 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9420. Min Act: -0.1700

Data Index: 706138 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9420. Min Act: -0.1700

Data Index: 497920 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9420. Min Act: -0.1700

Data Index: 1109613 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.9420. Min Act: -0.1700

Data Index: 522215 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 5.1920. Min Range: -5.1920

Max Act: 4.8795. Min Act: -0.1700

Data Index: 1072561 (C4 (Web Text))

Max Activating Token Index: 154