Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.4003. Min Act: -0.1700
Data Index: 836882 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.3691. Min Act: -0.1700
Data Index: 3748420 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.3065. Min Act: -0.1700
Data Index: 4174291 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.2128. Min Act: -0.1700
Data Index: 8745027 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.1815. Min Act: -0.1700
Data Index: 5099950 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.1815. Min Act: -0.1700
Data Index: 2819303 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.1190. Min Act: -0.1700
Data Index: 5247455 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0878. Min Act: -0.1700
Data Index: 7767623 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0878. Min Act: -0.1700
Data Index: 5563523 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0565. Min Act: -0.1700
Data Index: 519096 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0565. Min Act: -0.1700
Data Index: 519097 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0565. Min Act: -0.1700
Data Index: 3953961 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0565. Min Act: -0.1700
Data Index: 3062445 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0252. Min Act: -0.1700
Data Index: 5394942 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0252. Min Act: -0.1700
Data Index: 6412405 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0252. Min Act: -0.1700
Data Index: 1027528 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0252. Min Act: -0.1700
Data Index: 6412404 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4003. Min Range: -4.4003
Max Act: 4.0252. Min Act: -0.1700
Data Index: 1027529 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4003. Min Range: -4.4003
Max Act: 3.9940. Min Act: -0.1700
Data Index: 3953960 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4003. Min Range: -4.4003
Max Act: 3.9940. Min Act: -0.1700
Data Index: 863323 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19