Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.4654. Min Act: -0.1700
Data Index: 5273900 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.3404. Min Act: -0.1700
Data Index: 6065513 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.3092. Min Act: -0.1700
Data Index: 5220169 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.2779. Min Act: -0.1700
Data Index: 1451687 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.2154. Min Act: -0.1700
Data Index: 788955 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.2154. Min Act: -0.1700
Data Index: 3317884 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.1529. Min Act: -0.1700
Data Index: 1638680 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.1217. Min Act: -0.1700
Data Index: 591243 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.0904. Min Act: -0.1700
Data Index: 5248977 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4654. Min Range: -6.4654
Max Act: 6.0592. Min Act: -0.1700
Data Index: 3715800 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9967. Min Act: -0.1700
Data Index: 2107423 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9967. Min Act: -0.1700
Data Index: 4105305 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9967. Min Act: -0.1700
Data Index: 2074162 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9967. Min Act: -0.1700
Data Index: 248941 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9967. Min Act: -0.1700
Data Index: 4099075 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9654. Min Act: -0.1700
Data Index: 6704076 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9654. Min Act: -0.1700
Data Index: 3589214 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9654. Min Act: -0.1700
Data Index: 3784003 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9654. Min Act: -0.1700
Data Index: 1366588 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4654. Min Range: -6.4654
Max Act: 5.9654. Min Act: -0.1700
Data Index: 4651114 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19