Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.9259. Min Act: -0.1700
Data Index: 643620 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8946. Min Act: -0.1700
Data Index: 6260628 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8321. Min Act: -0.1700
Data Index: 1576766 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8009. Min Act: -0.1700
Data Index: 8663452 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8009. Min Act: -0.1700
Data Index: 6750805 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7696. Min Act: -0.1700
Data Index: 895778 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7696. Min Act: -0.1700
Data Index: 1313621 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7696. Min Act: -0.1700
Data Index: 6268610 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 3226908 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7696. Min Act: -0.1700
Data Index: 5601504 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 3218339 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 6217390 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 6349779 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 7325485 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 1231449 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 3055692 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 5914573 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 753024 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 1278992 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 3469278 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19