Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5388 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9720. Min Act: -0.1700
Data Index: 2984018 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9095. Min Act: -0.1700
Data Index: 1779407 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9095. Min Act: -0.1700
Data Index: 3629613 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9408. Min Act: -0.1700
Data Index: 6201728 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9095. Min Act: -0.1700
Data Index: 1524581 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9095. Min Act: -0.1700
Data Index: 837143 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8783. Min Act: -0.1700
Data Index: 6763068 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9095. Min Act: -0.1700
Data Index: 470847 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8783. Min Act: -0.1700
Data Index: 2743259 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8470. Min Act: -0.1700
Data Index: 4187331 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8470. Min Act: -0.1700
Data Index: 6983412 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8158. Min Act: -0.1700
Data Index: 6835878 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8158. Min Act: -0.1700
Data Index: 2003083 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8158. Min Act: -0.1700
Data Index: 7246212 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8158. Min Act: -0.1700
Data Index: 94358 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7845. Min Act: -0.1700
Data Index: 482299 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7845. Min Act: -0.1700
Data Index: 6325249 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7845. Min Act: -0.1700
Data Index: 2267010 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7845. Min Act: -0.1700
Data Index: 2523476 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7845. Min Act: -0.1700
Data Index: 6499977 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19