Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4456 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1712. Min Range: -7.1712
Max Act: 7.1712. Min Act: -0.1700
Data Index: 3743268 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.9524. Min Act: -0.1700
Data Index: 2138507 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7649. Min Act: -0.1700
Data Index: 6734284 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7337. Min Act: -0.1700
Data Index: 4526730 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7024. Min Act: -0.1700
Data Index: 5385635 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.6712. Min Act: -0.1700
Data Index: 5758375 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.6399. Min Act: -0.1700
Data Index: 7825246 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.6399. Min Act: -0.1700
Data Index: 6096901 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.5462. Min Act: -0.1700
Data Index: 3589844 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.5149. Min Act: -0.1700
Data Index: 6254576 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.5149. Min Act: -0.1700
Data Index: 1744533 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.5149. Min Act: -0.1700
Data Index: 6838154 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.5149. Min Act: -0.1700
Data Index: 2345836 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.4837. Min Act: -0.1700
Data Index: 7463539 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.4837. Min Act: -0.1700
Data Index: 2211031 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.4837. Min Act: -0.1700
Data Index: 5157050 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.4524. Min Act: -0.1700
Data Index: 50938 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.4837. Min Act: -0.1700
Data Index: 2062114 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.4524. Min Act: -0.1700
Data Index: 2807826 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.4524. Min Act: -0.1700
Data Index: 6496079 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19