Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.9217. Min Act: -0.1700
Data Index: 2960691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.8277. Min Act: -0.1700
Data Index: 868926 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.8277. Min Act: -0.1696
Data Index: 1286966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7934. Min Act: -0.1700
Data Index: 5449801 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7761. Min Act: -0.1700
Data Index: 4143557 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7761. Min Act: -0.1631
Data Index: 2393475 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7934. Min Act: -0.1700
Data Index: 5448447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7934. Min Act: -0.1700
Data Index: 7447296 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7934. Min Act: -0.1700
Data Index: 6043449 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7761. Min Act: -0.1700
Data Index: 5237502 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7761. Min Act: -0.1700
Data Index: 1078323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7675. Min Act: -0.1700
Data Index: 4802518 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7502. Min Act: -0.1333
Data Index: 2137427 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7330. Min Act: -0.1700
Data Index: 4744297 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7416. Min Act: -0.1700
Data Index: 7447297 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7416. Min Act: -0.1700
Data Index: 1256593 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7416. Min Act: -0.1700
Data Index: 4041814 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7243. Min Act: -0.1700
Data Index: 6766818 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7330. Min Act: -0.1700
Data Index: 478557 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9217. Min Range: -1.9217
Max Act: 1.7243. Min Act: -0.1700
Data Index: 2335045 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19