Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 711 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.3593. Min Act: -0.1700
Data Index: 8358809 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.2343. Min Act: -0.1700
Data Index: 8538914 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.2343. Min Act: -0.1700
Data Index: 3297921 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1718. Min Act: -0.1700
Data Index: 3968975 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1093. Min Act: -0.1700
Data Index: 5861878 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1093. Min Act: -0.1700
Data Index: 5948637 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1093. Min Act: -0.1700
Data Index: 2134824 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1093. Min Act: -0.1700
Data Index: 4949909 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.1093. Min Act: -0.1700
Data Index: 1135072 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 3694090 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.9843. Min Act: -0.1700
Data Index: 2807912 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 2034332 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 834041 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 6657491 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.9843. Min Act: -0.1700
Data Index: 4785217 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.9218. Min Act: -0.1700
Data Index: 1648871 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.9843. Min Act: -0.1700
Data Index: 6559368 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3593. Min Range: -8.3593
Max Act: 8.0468. Min Act: -0.1700
Data Index: 3715444 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.9843. Min Act: -0.1700
Data Index: 1359040 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3593. Min Range: -8.3593
Max Act: 7.9843. Min Act: -0.1700
Data Index: 7019132 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19