Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2762. Min Range: -9.2762
Max Act: 9.2762. Min Act: -0.1700
Data Index: 6446312 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2762. Min Range: -9.2762
Max Act: 9.0887. Min Act: -0.1700
Data Index: 2957166 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.9637. Min Act: -0.1700
Data Index: 4250354 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.9012. Min Act: -0.1700
Data Index: 7958873 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.8387. Min Act: -0.1700
Data Index: 292938 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.7762. Min Act: -0.1700
Data Index: 3663923 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.7137. Min Act: -0.1700
Data Index: 4675541 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.7137. Min Act: -0.1700
Data Index: 7087747 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.6512. Min Act: -0.1700
Data Index: 4859401 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.5262. Min Act: -0.1700
Data Index: 8376779 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.4637. Min Act: -0.1700
Data Index: 2019149 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.4637. Min Act: -0.1700
Data Index: 3470229 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.4637. Min Act: -0.1700
Data Index: 4630177 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.4012. Min Act: -0.1700
Data Index: 6360801 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.4012. Min Act: -0.1700
Data Index: 2579595 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.3387. Min Act: -0.1700
Data Index: 3137732 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.3387. Min Act: -0.1700
Data Index: 528946 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.3387. Min Act: -0.1700
Data Index: 6611500 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.2762. Min Act: -0.1700
Data Index: 2760946 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2762. Min Range: -9.2762
Max Act: 8.2137. Min Act: -0.1700
Data Index: 6625212 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19