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

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

Neuron 48 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: 9.0068. Min Range: -9.0068

Max Act: 9.0068. Min Act: -0.1700

Data Index: 693773 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.7881. Min Act: -0.1700

Data Index: 248848 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.6631. Min Act: -0.1700

Data Index: 1179579 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.6318. Min Act: -0.1700

Data Index: 437116 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.5068. Min Act: -0.1700

Data Index: 879194 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.4756. Min Act: -0.1700

Data Index: 1288930 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.5068. Min Act: -0.1700

Data Index: 768225 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.4756. Min Act: -0.1700

Data Index: 1200803 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.3818. Min Act: -0.1700

Data Index: 823917 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.2256. Min Act: -0.1700

Data Index: 946006 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1318. Min Act: -0.1700

Data Index: 97398 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1631. Min Act: -0.1700

Data Index: 1129463 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1006. Min Act: -0.1700

Data Index: 71395 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1631. Min Act: -0.1700

Data Index: 280793 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1943. Min Act: -0.1700

Data Index: 1017434 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.2568. Min Act: -0.1700

Data Index: 315507 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1631. Min Act: -0.1700

Data Index: 984045 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1006. Min Act: -0.1700

Data Index: 323865 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1006. Min Act: -0.1700

Data Index: 371726 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 9.0068. Min Range: -9.0068

Max Act: 8.1006. Min Act: -0.1700

Data Index: 197752 (C4 (Web Text))

Max Activating Token Index: 962