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

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

Neuron 1948 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: 3.7009. Min Range: -3.7009

Max Act: 3.6852. Min Act: -0.1700

Data Index: 1132419 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.6539. Min Act: -0.1700

Data Index: 166783 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.7009. Min Act: -0.1700

Data Index: 973766 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5913. Min Act: -0.1699

Data Index: 1065977 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.6383. Min Act: -0.1700

Data Index: 356935 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.6070. Min Act: -0.1700

Data Index: 226010 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5443. Min Act: -0.1700

Data Index: 1100332 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5600. Min Act: -0.1700

Data Index: 833212 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5600. Min Act: -0.1700

Data Index: 1040855 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1254076 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5757. Min Act: -0.1700

Data Index: 2660 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5600. Min Act: -0.1700

Data Index: 191505 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5130. Min Act: -0.1700

Data Index: 387171 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5443. Min Act: -0.1700

Data Index: 852187 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5130. Min Act: -0.1700

Data Index: 882787 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.4973. Min Act: -0.1700

Data Index: 435867 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.4973. Min Act: -0.1700

Data Index: 177869 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5287. Min Act: -0.1700

Data Index: 455839 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5130. Min Act: -0.1700

Data Index: 168950 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.4973. Min Act: -0.1700

Data Index: 380631 (C4 (Web Text))

Max Activating Token Index: 626