Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0297. Min Range: -8.0297
Max Act: 8.0297. Min Act: -0.1700
Data Index: 7690807 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.9047. Min Act: -0.1700
Data Index: 5915455 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6860. Min Act: -0.1700
Data Index: 3457774 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6860. Min Act: -0.1700
Data Index: 969466 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6860. Min Act: -0.1700
Data Index: 5006697 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6547. Min Act: -0.1700
Data Index: 7357716 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6547. Min Act: -0.1700
Data Index: 8722602 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6235. Min Act: -0.1700
Data Index: 28700 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5922. Min Act: -0.1700
Data Index: 7074485 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6547. Min Act: -0.1700
Data Index: 7665704 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.6547. Min Act: -0.1700
Data Index: 6410533 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5922. Min Act: -0.1700
Data Index: 4117909 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5922. Min Act: -0.1700
Data Index: 8551262 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5610. Min Act: -0.1700
Data Index: 4642313 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5610. Min Act: -0.1700
Data Index: 4324208 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5610. Min Act: -0.1700
Data Index: 5071221 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5610. Min Act: -0.1700
Data Index: 1903153 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5610. Min Act: -0.1700
Data Index: 4757292 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5610. Min Act: -0.1700
Data Index: 1037298 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0297. Min Range: -8.0297
Max Act: 7.5297. Min Act: -0.1700
Data Index: 5707148 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19