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

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

Neuron 1371 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: 3.6740. Min Range: -3.6740

Max Act: 3.6271. Min Act: -0.1700

Data Index: 149073 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.5958. Min Act: -0.1700

Data Index: 1080021 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.6740. Min Act: -0.1700

Data Index: 1255334 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.5018. Min Act: -0.1700

Data Index: 929237 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.5645. Min Act: -0.1700

Data Index: 119870 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.5645. Min Act: -0.1700

Data Index: 635956 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.5018. Min Act: -0.1700

Data Index: 1225213 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4391. Min Act: -0.1700

Data Index: 1342866 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4234. Min Act: -0.1700

Data Index: 50888 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.5018. Min Act: -0.1700

Data Index: 1024557 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4861. Min Act: -0.1700

Data Index: 1206939 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4548. Min Act: -0.1700

Data Index: 508513 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4705. Min Act: -0.1700

Data Index: 925699 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4705. Min Act: -0.1700

Data Index: 1064986 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4391. Min Act: -0.1700

Data Index: 1306245 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4391. Min Act: -0.1700

Data Index: 550070 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4077. Min Act: -0.1700

Data Index: 667658 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4077. Min Act: -0.1700

Data Index: 11065 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4548. Min Act: -0.1700

Data Index: 622866 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.4705. Min Act: -0.1700

Data Index: 193713 (C4 (Web Text))

Max Activating Token Index: 516