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

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

Neuron 1098 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.6419. Min Act: -0.1700

Data Index: 1291284 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5949. Min Act: -0.1700

Data Index: 915936 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5793. Min Act: -0.1700

Data Index: 920150 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5793. Min Act: -0.1700

Data Index: 88655 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5009. Min Act: -0.1700

Data Index: 789804 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5009. Min Act: -0.1700

Data Index: 1195399 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5636. Min Act: -0.1700

Data Index: 1289254 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5009. Min Act: -0.1700

Data Index: 1086059 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5166. Min Act: -0.1700

Data Index: 2639 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5009. Min Act: -0.1700

Data Index: 1212873 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5166. Min Act: -0.1700

Data Index: 158052 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4853. Min Act: -0.1700

Data Index: 999996 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.5009. Min Act: -0.1700

Data Index: 439924 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4853. Min Act: -0.1700

Data Index: 14372 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4853. Min Act: -0.1700

Data Index: 524076 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1357907 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4853. Min Act: -0.1700

Data Index: 50478 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4539. Min Act: -0.1700

Data Index: 492067 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4539. Min Act: -0.1700

Data Index: 221631 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 3.6419. Min Range: -3.6419

Max Act: 3.4696. Min Act: -0.1700

Data Index: 965387 (C4 (Web Text))

Max Activating Token Index: 248