Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0337. Min Range: -5.0337
Max Act: 5.0337. Min Act: -0.1700
Data Index: 8335866 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.9712. Min Act: -0.1700
Data Index: 6456176 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.8775. Min Act: -0.1700
Data Index: 8522538 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.8775. Min Act: -0.1700
Data Index: 1301536 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.8462. Min Act: -0.1700
Data Index: 631761 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.8150. Min Act: -0.1700
Data Index: 3542324 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.8150. Min Act: -0.1700
Data Index: 8203736 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.7837. Min Act: -0.1700
Data Index: 689892 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.8462. Min Act: -0.1700
Data Index: 4893844 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.7837. Min Act: -0.1700
Data Index: 4252144 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.7525. Min Act: -0.1700
Data Index: 5065156 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.7525. Min Act: -0.1700
Data Index: 4701763 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6900. Min Act: -0.1700
Data Index: 4701762 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6900. Min Act: -0.1700
Data Index: 8410074 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6900. Min Act: -0.1700
Data Index: 5802006 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6900. Min Act: -0.1700
Data Index: 2489954 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6900. Min Act: -0.1700
Data Index: 2744653 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6900. Min Act: -0.1700
Data Index: 4481309 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6900. Min Act: -0.1700
Data Index: 8255662 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0337. Min Range: -5.0337
Max Act: 4.6587. Min Act: -0.1700
Data Index: 8286152 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19