Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1701 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1898. Min Act: -0.1700

Data Index: 134694 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1583. Min Act: -0.1700

Data Index: 1016156 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1583. Min Act: -0.1700

Data Index: 165386 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1583. Min Act: -0.1700

Data Index: 1055773 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1583. Min Act: -0.1700

Data Index: 773836 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1268. Min Act: -0.1700

Data Index: 1138380 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1268. Min Act: -0.1700

Data Index: 418340 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1268. Min Act: -0.1700

Data Index: 465997 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1268. Min Act: -0.1700

Data Index: 464948 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0953. Min Act: -0.1700

Data Index: 1222181 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.1268. Min Act: -0.1700

Data Index: 728710 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0953. Min Act: -0.1700

Data Index: 128231 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0953. Min Act: -0.1700

Data Index: 792402 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0638. Min Act: -0.1700

Data Index: 403408 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0638. Min Act: -0.1700

Data Index: 812191 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0638. Min Act: -0.1700

Data Index: 1359326 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0322. Min Act: -0.1700

Data Index: 1097547 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0322. Min Act: -0.1700

Data Index: 418361 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0006. Min Act: -0.1700

Data Index: 551877 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 3.1898. Min Range: -3.1898

Max Act: 3.0006. Min Act: -0.1700

Data Index: 887696 (C4 (Web Text))

Max Activating Token Index: 608