Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1454 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8746. Min Act: -0.1700
Data Index: 3169603 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8746. Min Act: -0.1700
Data Index: 464987 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8434. Min Act: -0.1700
Data Index: 2098090 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8121. Min Act: -0.1700
Data Index: 8787936 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5451156 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5606032 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8121. Min Act: -0.1700
Data Index: 2119940 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5812844 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 5380271 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 4065214 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 7931845 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 7823718 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 1934938 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 6084332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7496. Min Act: -0.1700
Data Index: 3287690 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 1360773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 2328987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 479746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7809. Min Act: -0.1700
Data Index: 4946637 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8746. Min Range: -5.8746
Max Act: 5.7496. Min Act: -0.1700
Data Index: 4035670 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19