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

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

Neuron 1520 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.6348. Min Act: -0.1700

Data Index: 389102 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.1035. Min Act: -0.1700

Data Index: 1315568 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.0410. Min Act: -0.1700

Data Index: 522017 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 5.6348. Min Range: -5.6348

Max Act: 5.0098. Min Act: -0.1700

Data Index: 549140 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.9160. Min Act: -0.1700

Data Index: 445041 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8848. Min Act: -0.1700

Data Index: 618567 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8535. Min Act: -0.1700

Data Index: 836715 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.9160. Min Act: -0.1700

Data Index: 1230181 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.9160. Min Act: -0.1700

Data Index: 325149 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.9473. Min Act: -0.1700

Data Index: 1257950 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8848. Min Act: -0.1700

Data Index: 688800 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.7598. Min Act: -0.1700

Data Index: 922688 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8535. Min Act: -0.1700

Data Index: 529885 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8223. Min Act: -0.1700

Data Index: 937708 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8535. Min Act: -0.1700

Data Index: 265236 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8848. Min Act: -0.1700

Data Index: 353511 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8535. Min Act: -0.1700

Data Index: 616305 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.7910. Min Act: -0.1700

Data Index: 188739 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8223. Min Act: -0.1700

Data Index: 833324 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 5.6348. Min Range: -5.6348

Max Act: 4.8848. Min Act: -0.1700

Data Index: 358887 (C4 (Web Text))

Max Activating Token Index: 418