Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4340. Min Range: -8.4340
Max Act: 8.4340. Min Act: -0.1700
Data Index: 1022427 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4340. Min Range: -8.4340
Max Act: 8.3090. Min Act: -0.1700
Data Index: 5574911 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4340. Min Range: -8.4340
Max Act: 8.2465. Min Act: -0.1700
Data Index: 2795033 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4340. Min Range: -8.4340
Max Act: 8.1215. Min Act: -0.1700
Data Index: 7106518 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4340. Min Range: -8.4340
Max Act: 8.1215. Min Act: -0.1700
Data Index: 5978430 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4340. Min Range: -8.4340
Max Act: 8.1215. Min Act: -0.1700
Data Index: 4774343 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.9965. Min Act: -0.1700
Data Index: 7096246 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.9652. Min Act: -0.1700
Data Index: 8739696 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.9652. Min Act: -0.1700
Data Index: 4222505 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.9652. Min Act: -0.1700
Data Index: 7144796 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.8715. Min Act: -0.1700
Data Index: 5538394 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.9027. Min Act: -0.1700
Data Index: 4261956 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.9340. Min Act: -0.1700
Data Index: 3977617 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.8715. Min Act: -0.1700
Data Index: 6460071 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.8090. Min Act: -0.1700
Data Index: 8565461 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.8090. Min Act: -0.1700
Data Index: 3651885 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.8090. Min Act: -0.1700
Data Index: 4602915 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.8090. Min Act: -0.1700
Data Index: 3980564 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.7777. Min Act: -0.1700
Data Index: 6823457 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4340. Min Range: -8.4340
Max Act: 7.7465. Min Act: -0.1700
Data Index: 8345660 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19