Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1529 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.7330. Min Act: -0.1700

Data Index: 838909 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.7287. Min Act: -0.1700

Data Index: 4449 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.7006. Min Act: -0.1700

Data Index: 501207 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.7043. Min Act: -0.1700

Data Index: 661607 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.6709. Min Act: -0.1700

Data Index: 1046890 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.6599. Min Act: -0.1700

Data Index: 832375 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.6073. Min Act: -0.1700

Data Index: 1182843 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.6075. Min Act: -0.1700

Data Index: 1029246 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5628. Min Act: -0.1700

Data Index: 649101 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5696. Min Act: -0.1700

Data Index: 1074669 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5852. Min Act: -0.1700

Data Index: 940733 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5290. Min Act: -0.1700

Data Index: 868887 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5059. Min Act: -0.1700

Data Index: 618834 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5217. Min Act: -0.1700

Data Index: 649605 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5093. Min Act: -0.1639

Data Index: 1155173 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.5081. Min Act: -0.1700

Data Index: 326516 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.4890. Min Act: -0.1700

Data Index: 546722 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.4804. Min Act: -0.1698

Data Index: 16857 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.4937. Min Act: -0.1700

Data Index: 84965 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 4.7330. Min Range: -4.7330

Max Act: 4.4939. Min Act: -0.1700

Data Index: 102201 (C4 (Web Text))

Max Activating Token Index: 262