Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.3558. Min Act: -0.1700
Data Index: 2751084 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.2933. Min Act: -0.1700
Data Index: 4299390 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.2933. Min Act: -0.1700
Data Index: 2706519 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.2621. Min Act: -0.1700
Data Index: 624949 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1683. Min Act: -0.1700
Data Index: 8738474 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1371. Min Act: -0.1700
Data Index: 2035699 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1683. Min Act: -0.1700
Data Index: 4299391 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1996. Min Act: -0.1700
Data Index: 278340 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1683. Min Act: -0.1700
Data Index: 3140720 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1683. Min Act: -0.1700
Data Index: 8249128 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1371. Min Act: -0.1700
Data Index: 7089239 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1371. Min Act: -0.1700
Data Index: 3628459 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1058. Min Act: -0.1700
Data Index: 5396946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1371. Min Act: -0.1700
Data Index: 2941473 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.0745. Min Act: -0.1700
Data Index: 5023640 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.0745. Min Act: -0.1700
Data Index: 7888901 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.0745. Min Act: -0.1700
Data Index: 4659166 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.1058. Min Act: -0.1700
Data Index: 7904843 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.0745. Min Act: -0.1700
Data Index: 4647372 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3558. Min Range: -4.3558
Max Act: 4.0433. Min Act: -0.1700
Data Index: 1877239 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19