Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.7797. Min Act: -0.1700
Data Index: 5716992 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.7172. Min Act: -0.1700
Data Index: 8280800 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.6547. Min Act: -0.1700
Data Index: 474327 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.4359. Min Act: -0.1700
Data Index: 1645759 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.4047. Min Act: -0.1700
Data Index: 7874975 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.4047. Min Act: -0.1700
Data Index: 1891569 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.4047. Min Act: -0.1700
Data Index: 8634306 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3734. Min Act: -0.1700
Data Index: 4768297 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3422. Min Act: -0.1700
Data Index: 8457915 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 1065189 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 6200302 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 310342 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 857432 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 3448589 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 3878571 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 4090122 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.3109. Min Act: -0.1700
Data Index: 2268933 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.2484. Min Act: -0.1700
Data Index: 820830 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.2797. Min Act: -0.1700
Data Index: 7609691 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7797. Min Range: -5.7797
Max Act: 5.2797. Min Act: -0.1700
Data Index: 4052146 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19