Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 92 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0928. Min Range: -4.0928
Max Act: 4.0928. Min Act: -0.1700
Data Index: 403153 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9990. Min Act: -0.1700
Data Index: 568772 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9990. Min Act: -0.1700
Data Index: 663037 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0928. Min Range: -4.0928
Max Act: 4.0303. Min Act: -0.1700
Data Index: 716225 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9678. Min Act: -0.1700
Data Index: 1347051 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9678. Min Act: -0.1700
Data Index: 636013 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9365. Min Act: -0.1700
Data Index: 306842 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9365. Min Act: -0.1700
Data Index: 729921 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9365. Min Act: -0.1700
Data Index: 248666 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9052. Min Act: -0.1700
Data Index: 1377107 (Python Code)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9052. Min Act: -0.1700
Data Index: 1382641 (Python Code)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9052. Min Act: -0.1700
Data Index: 1541085 (Python Code)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9052. Min Act: -0.1700
Data Index: 560952 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9052. Min Act: -0.1700
Data Index: 244070 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.9052. Min Act: -0.1700
Data Index: 563810 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.8740. Min Act: -0.1700
Data Index: 920603 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.8740. Min Act: -0.1700
Data Index: 400142 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.8740. Min Act: -0.1700
Data Index: 314178 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.8427. Min Act: -0.1700
Data Index: 1319584 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0928. Min Range: -4.0928
Max Act: 3.8740. Min Act: -0.1700
Data Index: 268121 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19