Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3870 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.6696. Min Act: -0.1700
Data Index: 2009481 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.5446. Min Act: -0.1700
Data Index: 6111117 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.5446. Min Act: -0.1700
Data Index: 6093416 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.4821. Min Act: -0.1700
Data Index: 8732690 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.3571. Min Act: -0.1700
Data Index: 467704 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.2946. Min Act: -0.1700
Data Index: 7233180 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.2321. Min Act: -0.1700
Data Index: 1738153 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.1696. Min Act: -0.1700
Data Index: 8022090 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.1696. Min Act: -0.1700
Data Index: 6334641 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.1071. Min Act: -0.1700
Data Index: 7492855 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.0446. Min Act: -0.1700
Data Index: 4485457 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.0446. Min Act: -0.1700
Data Index: 4362397 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.0446. Min Act: -0.1700
Data Index: 8622109 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.0133. Min Act: -0.1700
Data Index: 567201 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6696. Min Range: -8.6696
Max Act: 7.9821. Min Act: -0.1700
Data Index: 5184200 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6696. Min Range: -8.6696
Max Act: 8.0133. Min Act: -0.1700
Data Index: 1698978 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6696. Min Range: -8.6696
Max Act: 7.9196. Min Act: -0.1700
Data Index: 6095220 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6696. Min Range: -8.6696
Max Act: 7.9508. Min Act: -0.1700
Data Index: 8382121 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6696. Min Range: -8.6696
Max Act: 7.9508. Min Act: -0.1700
Data Index: 6285575 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6696. Min Range: -8.6696
Max Act: 7.9196. Min Act: -0.1700
Data Index: 7620066 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19