Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.4260. Min Act: -0.1700
Data Index: 933240 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.3010. Min Act: -0.1700
Data Index: 7734482 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.3010. Min Act: -0.1700
Data Index: 6500763 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.2385. Min Act: -0.1700
Data Index: 7083023 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.2385. Min Act: -0.1700
Data Index: 3862987 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.2073. Min Act: -0.1700
Data Index: 6200714 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1760. Min Act: -0.1700
Data Index: 6368813 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1760. Min Act: -0.1700
Data Index: 8352945 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1760. Min Act: -0.1700
Data Index: 1208645 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1760. Min Act: -0.1700
Data Index: 1339392 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1760. Min Act: -0.1700
Data Index: 8493372 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1448. Min Act: -0.1700
Data Index: 2926154 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1135. Min Act: -0.1700
Data Index: 7836100 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1135. Min Act: -0.1700
Data Index: 4662533 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.1135. Min Act: -0.1700
Data Index: 8036485 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.0510. Min Act: -0.1700
Data Index: 562542 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.0823. Min Act: -0.1700
Data Index: 8089090 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.0823. Min Act: -0.1700
Data Index: 5334946 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.0823. Min Act: -0.1700
Data Index: 4374772 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4260. Min Range: -5.4260
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3291465 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19