Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1572 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1865. Min Range: -4.1865

Max Act: 4.1865. Min Act: -0.1700

Data Index: 735846 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.9677. Min Act: -0.1700

Data Index: 1277713 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8582. Min Act: -0.1700

Data Index: 666420 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8895. Min Act: -0.1700

Data Index: 617932 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 4.1865. Min Range: -4.1865

Max Act: 4.0458. Min Act: -0.1700

Data Index: 222807 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7331. Min Act: -0.1700

Data Index: 89418 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8269. Min Act: -0.1700

Data Index: 1027506 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8113. Min Act: -0.1700

Data Index: 439537 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8269. Min Act: -0.1700

Data Index: 1390679 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8269. Min Act: -0.1700

Data Index: 517800 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7331. Min Act: -0.1700

Data Index: 805456 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7331. Min Act: -0.1700

Data Index: 901376 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7487. Min Act: -0.1700

Data Index: 1231656 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8269. Min Act: -0.1700

Data Index: 488225 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.6548. Min Act: -0.1700

Data Index: 385167 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.8426. Min Act: -0.1700

Data Index: 609623 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.6392. Min Act: -0.1700

Data Index: 561299 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7331. Min Act: -0.1700

Data Index: 1331303 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7174. Min Act: -0.1700

Data Index: 366808 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.7957. Min Act: -0.1700

Data Index: 961381 (C4 (Web Text))

Max Activating Token Index: 852