Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4661 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.7256. Min Act: -0.1700
Data Index: 1892597 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.6944. Min Act: -0.1700
Data Index: 2832848 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.6319. Min Act: -0.1700
Data Index: 5204752 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.5381. Min Act: -0.1700
Data Index: 5231717 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.5069. Min Act: -0.1700
Data Index: 7131581 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.5069. Min Act: -0.1700
Data Index: 1930775 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.4444. Min Act: -0.1700
Data Index: 7973106 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.4444. Min Act: -0.1700
Data Index: 566737 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.4131. Min Act: -0.1700
Data Index: 631668 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.4131. Min Act: -0.1700
Data Index: 6631283 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.3819. Min Act: -0.1700
Data Index: 614990 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.3819. Min Act: -0.1700
Data Index: 4555582 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.3819. Min Act: -0.1700
Data Index: 2584983 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.3506. Min Act: -0.1700
Data Index: 4810766 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2881. Min Act: -0.1700
Data Index: 1209127 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.3194. Min Act: -0.1700
Data Index: 1591846 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2881. Min Act: -0.1700
Data Index: 2140315 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2881. Min Act: -0.1700
Data Index: 273754 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2881. Min Act: -0.1700
Data Index: 5852863 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7256. Min Range: -6.7256
Max Act: 6.2569. Min Act: -0.1700
Data Index: 7564787 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19