Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.9198. Min Act: -0.1700
Data Index: 2500848 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.7634. Min Act: -0.1700
Data Index: 4544643 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.7009. Min Act: -0.1700
Data Index: 1339589 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.6696. Min Act: -0.1700
Data Index: 504290 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.6383. Min Act: -0.1700
Data Index: 2579347 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.6383. Min Act: -0.1700
Data Index: 2214785 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.6383. Min Act: -0.1700
Data Index: 7306619 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.6070. Min Act: -0.1700
Data Index: 874445 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 6154437 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 2983463 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 5618288 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 921222 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 6797351 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 646666 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 2489890 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5757. Min Act: -0.1700
Data Index: 6236338 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5600. Min Act: -0.1700
Data Index: 4872102 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5600. Min Act: -0.1700
Data Index: 8796159 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5600. Min Act: -0.1700
Data Index: 7386982 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9198. Min Range: -3.9198
Max Act: 3.5287. Min Act: -0.1700
Data Index: 2533822 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19