Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6340 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.5073. Min Act: -0.1700
Data Index: 4083040 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.4448. Min Act: -0.1700
Data Index: 8321221 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.3198. Min Act: -0.1700
Data Index: 1570993 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.2573. Min Act: -0.1700
Data Index: 6001528 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.2573. Min Act: -0.1700
Data Index: 7581605 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.2573. Min Act: -0.1700
Data Index: 5318701 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.2573. Min Act: -0.1700
Data Index: 3468998 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.1323. Min Act: -0.1700
Data Index: 4991968 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.1323. Min Act: -0.1700
Data Index: 5517817 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.0698. Min Act: -0.1700
Data Index: 4091865 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.0698. Min Act: -0.1700
Data Index: 3251638 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.0073. Min Act: -0.1700
Data Index: 2976269 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5073. Min Range: -9.5073
Max Act: 9.0073. Min Act: -0.1700
Data Index: 3196951 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5073. Min Range: -9.5073
Max Act: 8.9448. Min Act: -0.1700
Data Index: 2055689 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5073. Min Range: -9.5073
Max Act: 8.8823. Min Act: -0.1700
Data Index: 3975203 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5073. Min Range: -9.5073
Max Act: 8.8823. Min Act: -0.1700
Data Index: 3396616 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5073. Min Range: -9.5073
Max Act: 8.8823. Min Act: -0.1700
Data Index: 4492598 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5073. Min Range: -9.5073
Max Act: 8.8823. Min Act: -0.1700
Data Index: 3783265 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5073. Min Range: -9.5073
Max Act: 8.8823. Min Act: -0.1700
Data Index: 6568988 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5073. Min Range: -9.5073
Max Act: 8.8198. Min Act: -0.1700
Data Index: 1804201 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19