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

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

Neuron 146 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: 5.4017. Min Range: -5.4017

Max Act: 5.4017. Min Act: -0.1699

Data Index: 1134791 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.3080. Min Act: -0.1700

Data Index: 307390 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.3705. Min Act: -0.1700

Data Index: 907249 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.3392. Min Act: -0.1700

Data Index: 682560 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.2767. Min Act: -0.1700

Data Index: 633162 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1830. Min Act: -0.1700

Data Index: 202817 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.2142. Min Act: -0.1700

Data Index: 140746 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.2142. Min Act: -0.1700

Data Index: 1022092 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.2142. Min Act: -0.1699

Data Index: 360722 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1830. Min Act: -0.1700

Data Index: 1257290 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1830. Min Act: -0.1700

Data Index: 1280428 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1830. Min Act: -0.1700

Data Index: 643545 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1830. Min Act: -0.1700

Data Index: 613740 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1517. Min Act: -0.1689

Data Index: 945085 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1517. Min Act: -0.1699

Data Index: 59343 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1205. Min Act: -0.1700

Data Index: 1106882 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1517. Min Act: -0.1700

Data Index: 22603 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.0892. Min Act: -0.1700

Data Index: 109060 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1517. Min Act: -0.1700

Data Index: 395949 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 5.4017. Min Range: -5.4017

Max Act: 5.1205. Min Act: -0.1700

Data Index: 606409 (C4 (Web Text))

Max Activating Token Index: 188