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

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

Neuron 1698 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: 3.6521. Min Range: -3.6521

Max Act: 3.6521. Min Act: -0.1700

Data Index: 456600 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.6521. Min Act: -0.1700

Data Index: 843104 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.6208. Min Act: -0.1700

Data Index: 677967 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.5895. Min Act: -0.1700

Data Index: 935286 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.5581. Min Act: -0.1700

Data Index: 438032 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4955. Min Act: -0.1700

Data Index: 1287100 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.5268. Min Act: -0.1700

Data Index: 389796 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.5268. Min Act: -0.1700

Data Index: 259501 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4955. Min Act: -0.1700

Data Index: 973822 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4641. Min Act: -0.1700

Data Index: 17456 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4641. Min Act: -0.1700

Data Index: 906050 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4641. Min Act: -0.1700

Data Index: 83963 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4328. Min Act: -0.1700

Data Index: 1265255 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4328. Min Act: -0.1700

Data Index: 222175 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4328. Min Act: -0.1700

Data Index: 1155413 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4328. Min Act: -0.1700

Data Index: 919910 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4641. Min Act: -0.1700

Data Index: 1188609 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4328. Min Act: -0.1700

Data Index: 298591 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4014. Min Act: -0.1700

Data Index: 277020 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 3.6521. Min Range: -3.6521

Max Act: 3.4014. Min Act: -0.1700

Data Index: 961012 (C4 (Web Text))

Max Activating Token Index: 242