Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1068 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6459523 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.5359. Min Act: -0.1700
Data Index: 5394679 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6608883 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.5047. Min Act: -0.1700
Data Index: 628851 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.2859. Min Act: -0.1700
Data Index: 6649006 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.2859. Min Act: -0.1700
Data Index: 4369130 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.2859. Min Act: -0.1700
Data Index: 2398042 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.2547. Min Act: -0.1700
Data Index: 1216849 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.2547. Min Act: -0.1700
Data Index: 5880789 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.2234. Min Act: -0.1700
Data Index: 5040609 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.2234. Min Act: -0.1700
Data Index: 1177125 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.1609. Min Act: -0.1700
Data Index: 3082763 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.1922. Min Act: -0.1700
Data Index: 6099365 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.1297. Min Act: -0.1700
Data Index: 4800772 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.1609. Min Act: -0.1700
Data Index: 3463796 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.1297. Min Act: -0.1700
Data Index: 5436712 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.1297. Min Act: -0.1700
Data Index: 5304468 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.1297. Min Act: -0.1700
Data Index: 1080681 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.0984. Min Act: -0.1700
Data Index: 6172441 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5359. Min Range: -5.5359
Max Act: 5.0984. Min Act: -0.1700
Data Index: 5394677 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19