Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1092 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1086. Min Range: -6.1086
Max Act: 6.1086. Min Act: -0.1700
Data Index: 1624086 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.9836. Min Act: -0.1700
Data Index: 5614183 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.8899. Min Act: -0.1700
Data Index: 6935447 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.8586. Min Act: -0.1700
Data Index: 2766257 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7961. Min Act: -0.1700
Data Index: 5186361 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7961. Min Act: -0.1700
Data Index: 2286159 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7649. Min Act: -0.1700
Data Index: 6754064 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7649. Min Act: -0.1700
Data Index: 905820 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7336. Min Act: -0.1700
Data Index: 3819379 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6711. Min Act: -0.1700
Data Index: 259701 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6711. Min Act: -0.1700
Data Index: 2625991 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 6759694 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 7207068 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 7210470 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 4640195 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 1494756 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 2781203 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 6591027 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.5774. Min Act: -0.1700
Data Index: 4416452 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 5201882 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19