Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4555 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.4985. Min Act: -0.1700
Data Index: 7063003 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.4047. Min Act: -0.1700
Data Index: 3763614 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.3422. Min Act: -0.1700
Data Index: 3198782 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.3422. Min Act: -0.1700
Data Index: 2229321 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.3422. Min Act: -0.1700
Data Index: 4130078 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.3110. Min Act: -0.1700
Data Index: 6462061 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.2485. Min Act: -0.1700
Data Index: 5637838 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.2172. Min Act: -0.1700
Data Index: 7013807 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.2172. Min Act: -0.1700
Data Index: 5743916 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1860. Min Act: -0.1700
Data Index: 3794502 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.2172. Min Act: -0.1700
Data Index: 231504 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1860. Min Act: -0.1700
Data Index: 7140371 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1547. Min Act: -0.1700
Data Index: 2898566 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1547. Min Act: -0.1700
Data Index: 7575428 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1547. Min Act: -0.1700
Data Index: 5778489 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1547. Min Act: -0.1700
Data Index: 6547184 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1547. Min Act: -0.1700
Data Index: 5141540 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1547. Min Act: -0.1700
Data Index: 6766233 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1235. Min Act: -0.1700
Data Index: 101142 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4985. Min Range: -5.4985
Max Act: 5.1235. Min Act: -0.1700
Data Index: 5854425 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19