Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.8329. Min Act: -0.1700
Data Index: 6182746 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.7079. Min Act: -0.1700
Data Index: 1390648 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.6454. Min Act: -0.1700
Data Index: 7711396 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.6141. Min Act: -0.1700
Data Index: 6280351 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.6141. Min Act: -0.1700
Data Index: 6054613 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.5829. Min Act: -0.1700
Data Index: 5531812 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.5204. Min Act: -0.1700
Data Index: 6142658 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.5204. Min Act: -0.1700
Data Index: 6251395 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4891. Min Act: -0.1700
Data Index: 4200475 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4891. Min Act: -0.1700
Data Index: 5257156 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4891. Min Act: -0.1700
Data Index: 4115072 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4579. Min Act: -0.1700
Data Index: 2965361 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4579. Min Act: -0.1700
Data Index: 2490713 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4579. Min Act: -0.1700
Data Index: 814335 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4266. Min Act: -0.1700
Data Index: 4787035 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4266. Min Act: -0.1700
Data Index: 7900697 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4266. Min Act: -0.1700
Data Index: 2278556 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4266. Min Act: -0.1700
Data Index: 1823162 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.3954. Min Act: -0.1700
Data Index: 3790882 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8329. Min Range: -4.8329
Max Act: 4.4266. Min Act: -0.1700
Data Index: 7092999 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19