Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0133. Min Range: -8.0133
Max Act: 8.0133. Min Act: -0.1700
Data Index: 5579908 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.8258. Min Act: -0.1700
Data Index: 5831448 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.6383. Min Act: -0.1700
Data Index: 6452649 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.5758. Min Act: -0.1700
Data Index: 1527609 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.4508. Min Act: -0.1700
Data Index: 2542692 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.4508. Min Act: -0.1700
Data Index: 1180900 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.5133. Min Act: -0.1700
Data Index: 8518184 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3883. Min Act: -0.1700
Data Index: 322530 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.4508. Min Act: -0.1700
Data Index: 2201972 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3883. Min Act: -0.1700
Data Index: 1946852 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3883. Min Act: -0.1700
Data Index: 1727295 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.4195. Min Act: -0.1700
Data Index: 7903850 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3883. Min Act: -0.1700
Data Index: 6968680 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.4195. Min Act: -0.1700
Data Index: 2653162 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.4195. Min Act: -0.1700
Data Index: 5807456 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3570. Min Act: -0.1700
Data Index: 7005386 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3570. Min Act: -0.1700
Data Index: 2069142 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3570. Min Act: -0.1700
Data Index: 3726184 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.2945. Min Act: -0.1700
Data Index: 364331 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0133. Min Range: -8.0133
Max Act: 7.3258. Min Act: -0.1700
Data Index: 514239 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19