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

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

Neuron 1796 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.4792. Min Act: -0.1700

Data Index: 438845 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.3851. Min Act: -0.1700

Data Index: 31964 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.3223. Min Act: -0.1700

Data Index: 518575 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.3223. Min Act: -0.1700

Data Index: 437472 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.3223. Min Act: -0.1700

Data Index: 226476 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.3223. Min Act: -0.1700

Data Index: 565985 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.3066. Min Act: -0.1700

Data Index: 661161 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.3066. Min Act: -0.1700

Data Index: 965899 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2909. Min Act: -0.1700

Data Index: 642106 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2909. Min Act: -0.1700

Data Index: 1069512 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2909. Min Act: -0.1700

Data Index: 59486 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2595. Min Act: -0.1700

Data Index: 1192362 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2595. Min Act: -0.1700

Data Index: 641993 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2438. Min Act: -0.1700

Data Index: 644388 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2595. Min Act: -0.1700

Data Index: 166611 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2438. Min Act: -0.1700

Data Index: 515264 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2281. Min Act: -0.1700

Data Index: 167388 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2438. Min Act: -0.1700

Data Index: 200369 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.2281. Min Act: -0.1700

Data Index: 1028450 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 3.4792. Min Range: -3.4792

Max Act: 3.1966. Min Act: -0.1700

Data Index: 476187 (C4 (Web Text))

Max Activating Token Index: 172