Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.5791. Min Act: -0.1700
Data Index: 852010 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.3603. Min Act: -0.1700
Data Index: 6628511 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.1728. Min Act: -0.1700
Data Index: 3224675 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.1728. Min Act: -0.1700
Data Index: 5859854 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.1728. Min Act: -0.1700
Data Index: 7745744 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.1416. Min Act: -0.1700
Data Index: 322207 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.1416. Min Act: -0.1700
Data Index: 4845236 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.0790. Min Act: -0.1700
Data Index: 3932834 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.0790. Min Act: -0.1700
Data Index: 489611 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.0478. Min Act: -0.1700
Data Index: 767315 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.0165. Min Act: -0.1700
Data Index: 5830088 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.0165. Min Act: -0.1700
Data Index: 8137668 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5791. Min Range: -4.5791
Max Act: 3.9853. Min Act: -0.1700
Data Index: 700900 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.0165. Min Act: -0.1700
Data Index: 6504799 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5791. Min Range: -4.5791
Max Act: 3.9853. Min Act: -0.1700
Data Index: 7316437 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5791. Min Range: -4.5791
Max Act: 4.0165. Min Act: -0.1700
Data Index: 8117064 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5791. Min Range: -4.5791
Max Act: 3.9853. Min Act: -0.1700
Data Index: 1106381 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5791. Min Range: -4.5791
Max Act: 3.9853. Min Act: -0.1700
Data Index: 7758807 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5791. Min Range: -4.5791
Max Act: 3.9540. Min Act: -0.1700
Data Index: 4103761 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5791. Min Range: -4.5791
Max Act: 3.9540. Min Act: -0.1700
Data Index: 8697435 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19