Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2071 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.4600. Min Act: -0.1700
Data Index: 5353183 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.4600. Min Act: -0.1700
Data Index: 5353182 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.4600. Min Act: -0.1700
Data Index: 5353172 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.4160. Min Act: -0.1700
Data Index: 6161685 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.4072. Min Act: -0.1700
Data Index: 3211742 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.4072. Min Act: -0.1700
Data Index: 2384865 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3896. Min Act: -0.1700
Data Index: 4159015 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3984. Min Act: -0.1700
Data Index: 5353171 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3984. Min Act: -0.1700
Data Index: 4480714 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3984. Min Act: -0.1700
Data Index: 2388511 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3984. Min Act: -0.1700
Data Index: 2030264 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3808. Min Act: -0.1700
Data Index: 7770325 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3896. Min Act: -0.1700
Data Index: 186613 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3896. Min Act: -0.1700
Data Index: 7191067 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3896. Min Act: -0.1700
Data Index: 1060237 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3808. Min Act: -0.1700
Data Index: 4159026 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3808. Min Act: -0.1700
Data Index: 6587148 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3808. Min Act: -0.1700
Data Index: 4541247 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3808. Min Act: -0.1700
Data Index: 6270018 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4600. Min Range: -1.4600
Max Act: 1.3808. Min Act: -0.1700
Data Index: 3021401 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19