Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3712 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.5278. Min Act: -0.1700
Data Index: 2338401 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.2778. Min Act: -0.1700
Data Index: 6540971 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.2778. Min Act: -0.1700
Data Index: 2075234 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.2466. Min Act: -0.1700
Data Index: 5154681 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.1528. Min Act: -0.1700
Data Index: 1630876 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.1216. Min Act: -0.1700
Data Index: 5217937 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.1216. Min Act: -0.1700
Data Index: 817010 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.0591. Min Act: -0.1700
Data Index: 8423183 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.0591. Min Act: -0.1700
Data Index: 3588346 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5278. Min Range: -6.5278
Max Act: 6.0278. Min Act: -0.1700
Data Index: 2084253 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9966. Min Act: -0.1700
Data Index: 7113706 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9966. Min Act: -0.1700
Data Index: 7404632 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9966. Min Act: -0.1700
Data Index: 1116874 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9966. Min Act: -0.1700
Data Index: 2812526 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9966. Min Act: -0.1700
Data Index: 2970873 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9653. Min Act: -0.1700
Data Index: 8325503 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9653. Min Act: -0.1700
Data Index: 6886327 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9341. Min Act: -0.1700
Data Index: 802448 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9653. Min Act: -0.1700
Data Index: 7574165 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5278. Min Range: -6.5278
Max Act: 5.9341. Min Act: -0.1700
Data Index: 6958552 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19