Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4882 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.7148. Min Act: -0.1700
Data Index: 8720033 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.5585. Min Act: -0.1700
Data Index: 4106656 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.4960. Min Act: -0.1700
Data Index: 693086 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.4335. Min Act: -0.1700
Data Index: 4104874 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.3398. Min Act: -0.1700
Data Index: 3349131 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.3398. Min Act: -0.1700
Data Index: 2688845 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.3085. Min Act: -0.1700
Data Index: 3636077 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.2773. Min Act: -0.1700
Data Index: 6732916 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.1523. Min Act: -0.1700
Data Index: 4104847 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.1210. Min Act: -0.1700
Data Index: 3914421 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.0898. Min Act: -0.1700
Data Index: 1229017 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.0585. Min Act: -0.1700
Data Index: 8590407 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.1210. Min Act: -0.1700
Data Index: 5647698 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.0898. Min Act: -0.1700
Data Index: 3601308 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.0898. Min Act: -0.1700
Data Index: 7272473 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7148. Min Range: -6.7148
Max Act: 6.0585. Min Act: -0.1700
Data Index: 4104868 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7148. Min Range: -6.7148
Max Act: 5.9960. Min Act: -0.1700
Data Index: 4104843 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7148. Min Range: -6.7148
Max Act: 5.9960. Min Act: -0.1700
Data Index: 4104856 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7148. Min Range: -6.7148
Max Act: 5.9960. Min Act: -0.1700
Data Index: 4104845 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7148. Min Range: -6.7148
Max Act: 5.9960. Min Act: -0.1700
Data Index: 2522572 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19