Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 863 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.9131. Min Act: -0.1700
Data Index: 3721601 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7256. Min Act: -0.1700
Data Index: 6785077 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7256. Min Act: -0.1700
Data Index: 7061857 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.7256. Min Act: -0.1700
Data Index: 5209966 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6944. Min Act: -0.1700
Data Index: 1925103 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6006. Min Act: -0.1700
Data Index: 340834 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6006. Min Act: -0.1700
Data Index: 1481882 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.6006. Min Act: -0.1700
Data Index: 6310291 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5381. Min Act: -0.1700
Data Index: 3136617 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5694. Min Act: -0.1700
Data Index: 839786 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5694. Min Act: -0.1700
Data Index: 1529212 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5381. Min Act: -0.1700
Data Index: 6154665 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5069. Min Act: -0.1700
Data Index: 7325510 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5381. Min Act: -0.1700
Data Index: 6793243 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5381. Min Act: -0.1700
Data Index: 3611846 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5069. Min Act: -0.1700
Data Index: 1306978 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5069. Min Act: -0.1700
Data Index: 480334 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5069. Min Act: -0.1700
Data Index: 2732243 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.5069. Min Act: -0.1700
Data Index: 2273573 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9131. Min Range: -4.9131
Max Act: 4.4756. Min Act: -0.1700
Data Index: 2889806 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19