Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 6 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.5910. Min Act: -0.1700

Data Index: 1236438 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.6380. Min Act: -0.1700

Data Index: 575052 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.5597. Min Act: -0.1700

Data Index: 39088 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.4344. Min Act: -0.1700

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.4344. Min Act: -0.1700

Data Index: 221943 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.4187. Min Act: -0.1700

Data Index: 630439 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3559. Min Act: -0.1700

Data Index: 584961 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3559. Min Act: -0.1700

Data Index: 904612 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3873. Min Act: -0.1700

Data Index: 92845 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3245. Min Act: -0.1700

Data Index: 554648 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.4187. Min Act: -0.1700

Data Index: 680336 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3873. Min Act: -0.1700

Data Index: 48130 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3873. Min Act: -0.1700

Data Index: 295904 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3716. Min Act: -0.1700

Data Index: 1011296 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3245. Min Act: -0.1700

Data Index: 869734 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.3245. Min Act: -0.1700

Data Index: 98375 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.2774. Min Act: -0.1700

Data Index: 877839 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.2931. Min Act: -0.1700

Data Index: 524082 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.2774. Min Act: -0.1700

Data Index: 691623 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.6380. Min Range: -3.6380

Max Act: 3.2931. Min Act: -0.1700

Data Index: 1023106 (C4 (Web Text))

Max Activating Token Index: 126