Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.5562. Min Act: -0.1700
Data Index: 4007960 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.4625. Min Act: -0.1700
Data Index: 2755852 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.4312. Min Act: -0.1700
Data Index: 2943392 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.4312. Min Act: -0.1700
Data Index: 7968630 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3687. Min Act: -0.1700
Data Index: 7190885 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3687. Min Act: -0.1700
Data Index: 648276 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3687. Min Act: -0.1700
Data Index: 435354 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3687. Min Act: -0.1700
Data Index: 8301795 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.4000. Min Act: -0.1700
Data Index: 4142084 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3687. Min Act: -0.1700
Data Index: 471699 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3062. Min Act: -0.1700
Data Index: 6928223 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3375. Min Act: -0.1700
Data Index: 6688718 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3062. Min Act: -0.1700
Data Index: 5136895 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3062. Min Act: -0.1700
Data Index: 2797768 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.3062. Min Act: -0.1700
Data Index: 7486750 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.2750. Min Act: -0.1700
Data Index: 848660 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.2750. Min Act: -0.1700
Data Index: 5136891 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.2750. Min Act: -0.1700
Data Index: 5136890 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.2750. Min Act: -0.1700
Data Index: 2797775 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5562. Min Range: -4.5562
Max Act: 4.2750. Min Act: -0.1700
Data Index: 848655 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19