Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2174 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.5208. Min Act: -0.1700
Data Index: 4266129 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3333. Min Act: -0.1700
Data Index: 7521081 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3333. Min Act: -0.1700
Data Index: 5809069 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3646. Min Act: -0.1700
Data Index: 693735 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3021. Min Act: -0.1700
Data Index: 824267 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3333. Min Act: -0.1700
Data Index: 7388850 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2083. Min Act: -0.1700
Data Index: 2857896 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3021. Min Act: -0.1700
Data Index: 317620 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2396. Min Act: -0.1700
Data Index: 7889189 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2083. Min Act: -0.1700
Data Index: 1835484 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1458. Min Act: -0.1700
Data Index: 3767889 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2083. Min Act: -0.1700
Data Index: 254610 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1771. Min Act: -0.1700
Data Index: 8496397 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7366858 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2396. Min Act: -0.1700
Data Index: 1801761 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1771. Min Act: -0.1700
Data Index: 2570778 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1771. Min Act: -0.1700
Data Index: 889299 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7865019 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1458. Min Act: -0.1700
Data Index: 3339354 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1771. Min Act: -0.1700
Data Index: 4897931 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19