Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3745. Min Range: -5.3745
Max Act: 5.3745. Min Act: -0.1700
Data Index: 5728315 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3745. Min Range: -5.3745
Max Act: 5.2183. Min Act: -0.1700
Data Index: 1158623 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3745. Min Range: -5.3745
Max Act: 5.1558. Min Act: -0.1700
Data Index: 7387862 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3745. Min Range: -5.3745
Max Act: 5.1245. Min Act: -0.1700
Data Index: 8537567 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3745. Min Range: -5.3745
Max Act: 5.0308. Min Act: -0.1700
Data Index: 7338922 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9995. Min Act: -0.1700
Data Index: 2401907 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9995. Min Act: -0.1700
Data Index: 3362867 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9995. Min Act: -0.1700
Data Index: 8506631 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9370. Min Act: -0.1700
Data Index: 2673648 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9370. Min Act: -0.1700
Data Index: 4968521 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9370. Min Act: -0.1700
Data Index: 7527318 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9058. Min Act: -0.1700
Data Index: 1672860 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9058. Min Act: -0.1700
Data Index: 2904483 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.9058. Min Act: -0.1700
Data Index: 641107 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.8745. Min Act: -0.1700
Data Index: 433215 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.8745. Min Act: -0.1700
Data Index: 99911 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.8745. Min Act: -0.1700
Data Index: 1526898 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.8745. Min Act: -0.1700
Data Index: 7100907 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.8433. Min Act: -0.1700
Data Index: 5229134 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3745. Min Range: -5.3745
Max Act: 4.8433. Min Act: -0.1700
Data Index: 5416757 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19