Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4020436 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.5727. Min Act: -0.1700
Data Index: 705 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.5102. Min Act: -0.1700
Data Index: 7567789 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.4790. Min Act: -0.1700
Data Index: 6179339 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.4165. Min Act: -0.1700
Data Index: 7661197 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.4165. Min Act: -0.1700
Data Index: 737111 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3852. Min Act: -0.1700
Data Index: 6592935 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3852. Min Act: -0.1700
Data Index: 200130 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3540. Min Act: -0.1700
Data Index: 6373157 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3540. Min Act: -0.1700
Data Index: 2578640 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3540. Min Act: -0.1700
Data Index: 1243523 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3540. Min Act: -0.1700
Data Index: 3773133 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3540. Min Act: -0.1700
Data Index: 7550946 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3227. Min Act: -0.1700
Data Index: 5658062 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3227. Min Act: -0.1700
Data Index: 5105324 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3227. Min Act: -0.1700
Data Index: 1415023 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3227. Min Act: -0.1700
Data Index: 1268964 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3227. Min Act: -0.1700
Data Index: 3388475 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3227. Min Act: -0.1700
Data Index: 2722221 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7602. Min Range: -5.7602
Max Act: 5.3227. Min Act: -0.1700
Data Index: 3940180 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19