Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5416 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.9769. Min Act: -0.1700
Data Index: 2282855 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.9144. Min Act: -0.1700
Data Index: 6095139 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.8519. Min Act: -0.1700
Data Index: 5155730 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.8206. Min Act: -0.1700
Data Index: 599913 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.8206. Min Act: -0.1700
Data Index: 5162821 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.8206. Min Act: -0.1700
Data Index: 5196592 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.7894. Min Act: -0.1700
Data Index: 1933423 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.7894. Min Act: -0.1700
Data Index: 5563237 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.7269. Min Act: -0.1700
Data Index: 1235943 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.7581. Min Act: -0.1700
Data Index: 3703820 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.7269. Min Act: -0.1700
Data Index: 8065059 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.7269. Min Act: -0.1700
Data Index: 7587814 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6956. Min Act: -0.1700
Data Index: 6673653 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6644. Min Act: -0.1700
Data Index: 1260467 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6644. Min Act: -0.1700
Data Index: 8465904 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6644. Min Act: -0.1700
Data Index: 3104456 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6644. Min Act: -0.1700
Data Index: 6812688 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6331. Min Act: -0.1700
Data Index: 1813839 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6331. Min Act: -0.1700
Data Index: 4714460 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9769. Min Range: -5.9769
Max Act: 5.6331. Min Act: -0.1700
Data Index: 8050948 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19