Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4832 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.6132. Min Act: -0.1700
Data Index: 6170441 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.5507. Min Act: -0.1700
Data Index: 6062887 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.5507. Min Act: -0.1700
Data Index: 4585834 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.5507. Min Act: -0.1700
Data Index: 5419132 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.5194. Min Act: -0.1700
Data Index: 5440113 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4882. Min Act: -0.1700
Data Index: 4740984 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.5194. Min Act: -0.1700
Data Index: 4369251 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4569. Min Act: -0.1700
Data Index: 6130268 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4882. Min Act: -0.1700
Data Index: 5051415 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4882. Min Act: -0.1700
Data Index: 4990116 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4569. Min Act: -0.1700
Data Index: 3087891 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4257. Min Act: -0.1700
Data Index: 6135808 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4257. Min Act: -0.1700
Data Index: 1380061 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4569. Min Act: -0.1700
Data Index: 3633820 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4257. Min Act: -0.1700
Data Index: 3528562 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4257. Min Act: -0.1700
Data Index: 7720062 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4257. Min Act: -0.1700
Data Index: 5890759 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4257. Min Act: -0.1700
Data Index: 4825063 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.4257. Min Act: -0.1700
Data Index: 8557775 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6132. Min Range: -4.6132
Max Act: 4.3632. Min Act: -0.1700
Data Index: 6987906 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19