Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5192 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4154. Min Range: -12.4154
Max Act: 12.4154. Min Act: -0.1700
Data Index: 1623435 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4154. Min Range: -12.4154
Max Act: 12.1654. Min Act: -0.1700
Data Index: 6516038 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4154. Min Range: -12.4154
Max Act: 12.1029. Min Act: -0.1700
Data Index: 3535332 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.7904. Min Act: -0.1700
Data Index: 6941727 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.7279. Min Act: -0.1700
Data Index: 1331530 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.6654. Min Act: -0.1700
Data Index: 5231778 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.6654. Min Act: -0.1700
Data Index: 1930523 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.6029. Min Act: -0.1700
Data Index: 4007370 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.5404. Min Act: -0.1700
Data Index: 8255810 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.4154. Min Act: -0.1700
Data Index: 8128575 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.4779. Min Act: -0.1700
Data Index: 763501 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.4779. Min Act: -0.1700
Data Index: 3866978 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.4779. Min Act: -0.1700
Data Index: 4180596 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.4779. Min Act: -0.1700
Data Index: 3727392 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.3529. Min Act: -0.1700
Data Index: 7429706 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.4154. Min Act: -0.1700
Data Index: 732090 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.4154. Min Act: -0.1700
Data Index: 4507064 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.2904. Min Act: -0.1700
Data Index: 6128595 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.2279. Min Act: -0.1700
Data Index: 1936395 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4154. Min Range: -12.4154
Max Act: 11.2279. Min Act: -0.1700
Data Index: 310546 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19