Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.5087. Min Act: -0.1700
Data Index: 6785192 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.4462. Min Act: -0.1700
Data Index: 5695875 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.3524. Min Act: -0.1700
Data Index: 8707467 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.2587. Min Act: -0.1700
Data Index: 954558 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.2587. Min Act: -0.1700
Data Index: 1728532 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.2587. Min Act: -0.1700
Data Index: 45409 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.2274. Min Act: -0.1700
Data Index: 3959160 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1962. Min Act: -0.1700
Data Index: 2976985 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1649. Min Act: -0.1700
Data Index: 6005995 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1649. Min Act: -0.1700
Data Index: 8409344 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1649. Min Act: -0.1700
Data Index: 848392 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1649. Min Act: -0.1700
Data Index: 3537027 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1337. Min Act: -0.1700
Data Index: 5385648 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1649. Min Act: -0.1700
Data Index: 8043224 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1024. Min Act: -0.1700
Data Index: 4143573 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1024. Min Act: -0.1700
Data Index: 2227736 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1024. Min Act: -0.1700
Data Index: 443722 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1024. Min Act: -0.1700
Data Index: 4615173 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.1024. Min Act: -0.1700
Data Index: 585891 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5087. Min Range: -5.5087
Max Act: 5.0712. Min Act: -0.1700
Data Index: 5823499 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19