Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 607 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.8779. Min Act: -0.1700
Data Index: 2309953 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.9404. Min Act: -0.1700
Data Index: 8408744 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.8779. Min Act: -0.1700
Data Index: 7525673 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.9091. Min Act: -0.1700
Data Index: 377799 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.8466. Min Act: -0.1700
Data Index: 7629272 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.8154. Min Act: -0.1700
Data Index: 23846 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.7529. Min Act: -0.1700
Data Index: 1236202 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.7529. Min Act: -0.1700
Data Index: 4774890 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6904. Min Act: -0.1700
Data Index: 8551606 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6591. Min Act: -0.1700
Data Index: 575553 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6904. Min Act: -0.1700
Data Index: 398056 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6904. Min Act: -0.1700
Data Index: 1707236 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.7216. Min Act: -0.1700
Data Index: 2459041 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6591. Min Act: -0.1700
Data Index: 5667771 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6904. Min Act: -0.1700
Data Index: 1859781 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6591. Min Act: -0.1700
Data Index: 5292486 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6279. Min Act: -0.1700
Data Index: 3832628 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.5966. Min Act: -0.1700
Data Index: 7638075 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6591. Min Act: -0.1700
Data Index: 528925 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9404. Min Range: -5.9404
Max Act: 5.6591. Min Act: -0.1700
Data Index: 3009581 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19