Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0935. Min Range: -4.0935
Max Act: 4.0935. Min Act: -0.1700
Data Index: 6541801 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0935. Min Range: -4.0935
Max Act: 4.0310. Min Act: -0.1700
Data Index: 3242588 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9997. Min Act: -0.1700
Data Index: 3762060 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9997. Min Act: -0.1700
Data Index: 7813793 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9684. Min Act: -0.1700
Data Index: 5223111 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9684. Min Act: -0.1700
Data Index: 1339839 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9372. Min Act: -0.1700
Data Index: 224066 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9059. Min Act: -0.1700
Data Index: 2688390 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9372. Min Act: -0.1700
Data Index: 3342849 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9372. Min Act: -0.1700
Data Index: 5920708 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9372. Min Act: -0.1700
Data Index: 421359 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9372. Min Act: -0.1700
Data Index: 7500444 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9059. Min Act: -0.1700
Data Index: 170180 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9059. Min Act: -0.1700
Data Index: 4452645 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.9059. Min Act: -0.1700
Data Index: 6795894 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.8747. Min Act: -0.1700
Data Index: 1440834 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.8747. Min Act: -0.1700
Data Index: 4224254 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.8434. Min Act: -0.1700
Data Index: 7426175 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.8434. Min Act: -0.1700
Data Index: 6435296 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0935. Min Range: -4.0935
Max Act: 3.8747. Min Act: -0.1700
Data Index: 4480895 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19