Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1150 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.4869. Min Act: -0.1700
Data Index: 5293037 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.3932. Min Act: -0.1700
Data Index: 1225814 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.3307. Min Act: -0.1700
Data Index: 4599963 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.3307. Min Act: -0.1700
Data Index: 3397483 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2994. Min Act: -0.1700
Data Index: 1668245 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 2098473 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 3431244 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 5761426 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 5652292 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 5261653 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 3436362 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 8239970 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2369. Min Act: -0.1700
Data Index: 5222481 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2369. Min Act: -0.1700
Data Index: 3461894 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2682. Min Act: -0.1700
Data Index: 3953298 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2369. Min Act: -0.1700
Data Index: 1376826 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.2369. Min Act: -0.1700
Data Index: 1583625 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.1744. Min Act: -0.1700
Data Index: 1583627 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.1744. Min Act: -0.1700
Data Index: 5814041 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4869. Min Range: -4.4869
Max Act: 4.1432. Min Act: -0.1700
Data Index: 5926425 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19