Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2519. Min Range: -6.2519
Max Act: 6.2519. Min Act: -0.1700
Data Index: 7804327 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2519. Min Range: -6.2519
Max Act: 6.1581. Min Act: -0.1700
Data Index: 253749 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2519. Min Range: -6.2519
Max Act: 6.1269. Min Act: -0.1700
Data Index: 105280 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2519. Min Range: -6.2519
Max Act: 6.0019. Min Act: -0.1700
Data Index: 5513442 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.9706. Min Act: -0.1700
Data Index: 5136636 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.9081. Min Act: -0.1700
Data Index: 7061844 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.9081. Min Act: -0.1700
Data Index: 2118466 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.8456. Min Act: -0.1700
Data Index: 7837813 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.8456. Min Act: -0.1700
Data Index: 84661 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.8769. Min Act: -0.1700
Data Index: 6257850 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.8456. Min Act: -0.1700
Data Index: 4251815 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.8144. Min Act: -0.1700
Data Index: 1030217 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.8144. Min Act: -0.1700
Data Index: 4166386 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.7831. Min Act: -0.1700
Data Index: 1097745 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2115973 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.7831. Min Act: -0.1700
Data Index: 3090207 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.7831. Min Act: -0.1700
Data Index: 5166437 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.7831. Min Act: -0.1700
Data Index: 3383970 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.7831. Min Act: -0.1700
Data Index: 559203 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2519. Min Range: -6.2519
Max Act: 5.7206. Min Act: -0.1700
Data Index: 2688138 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19