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

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

Neuron 1470 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.6052. Min Act: -0.1700

Data Index: 929468 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4799. Min Act: -0.1700

Data Index: 865846 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4329. Min Act: -0.1700

Data Index: 212734 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4799. Min Act: -0.1700

Data Index: 1118026 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4642. Min Act: -0.1700

Data Index: 388450 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4329. Min Act: -0.1700

Data Index: 527375 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4642. Min Act: -0.1700

Data Index: 714657 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4486. Min Act: -0.1700

Data Index: 759898 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4486. Min Act: -0.1700

Data Index: 239542 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4172. Min Act: -0.1700

Data Index: 258433 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4329. Min Act: -0.1700

Data Index: 1010588 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3858. Min Act: -0.1700

Data Index: 18040 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3858. Min Act: -0.1700

Data Index: 134454 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.4015. Min Act: -0.1700

Data Index: 1257270 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3701. Min Act: -0.1700

Data Index: 700868 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3545. Min Act: -0.1700

Data Index: 1354194 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3701. Min Act: -0.1700

Data Index: 374440 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3231. Min Act: -0.1700

Data Index: 1034706 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3388. Min Act: -0.1700

Data Index: 376979 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 3.6052. Min Range: -3.6052

Max Act: 3.3701. Min Act: -0.1700

Data Index: 203177 (C4 (Web Text))

Max Activating Token Index: 404