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

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

Neuron 19 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: 3.3106. Min Range: -3.3106

Max Act: 3.3106. Min Act: -0.1700

Data Index: 1226374 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.2635. Min Act: -0.1700

Data Index: 1194121 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.2163. Min Act: -0.1700

Data Index: 782105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.2321. Min Act: -0.1700

Data Index: 1222638 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.2006. Min Act: -0.1700

Data Index: 1337853 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1849. Min Act: -0.1700

Data Index: 926926 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1849. Min Act: -0.1700

Data Index: 373349 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1849. Min Act: -0.1700

Data Index: 723312 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1691. Min Act: -0.1700

Data Index: 414947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1534. Min Act: -0.1700

Data Index: 523782 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1219. Min Act: -0.1700

Data Index: 52778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1061. Min Act: -0.1700

Data Index: 1045544 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0746. Min Act: -0.1700

Data Index: 410616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0903. Min Act: -0.1700

Data Index: 940267 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0903. Min Act: -0.1700

Data Index: 277772 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1534. Min Act: -0.1700

Data Index: 1358759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0903. Min Act: -0.1700

Data Index: 1319976 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1080505 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1297777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.3106. Min Range: -3.3106

Max Act: 3.1061. Min Act: -0.1700

Data Index: 823198 (C4 (Web Text))

Max Activating Token Index: 1023