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

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

Neuron 175 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: 5.2047. Min Range: -5.2047

Max Act: 5.1422. Min Act: -0.1700

Data Index: 227463 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.2047. Min Act: -0.1700

Data Index: 1269177 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.1109. Min Act: -0.1700

Data Index: 981873 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0797. Min Act: -0.1700

Data Index: 687119 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0484. Min Act: -0.1700

Data Index: 263206 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.1109. Min Act: -0.1700

Data Index: 477697 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 587773 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0797. Min Act: -0.1700

Data Index: 665797 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 1324686 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0484. Min Act: -0.1700

Data Index: 1152464 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 1174139 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 856938 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 215899 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0484. Min Act: -0.1700

Data Index: 670397 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 95959 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 624504 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.9859. Min Act: -0.1700

Data Index: 265827 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.9859. Min Act: -0.1700

Data Index: 920973 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0172. Min Act: -0.1700

Data Index: 588123 (C4 (Web Text))

Max Activating Token Index: 174