Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4848 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0340. Min Range: -6.0340
Max Act: 6.0340. Min Act: -0.1700
Data Index: 2636862 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0340. Min Range: -6.0340
Max Act: 6.0340. Min Act: -0.1700
Data Index: 2644786 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.9715. Min Act: -0.1700
Data Index: 510525 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.9090. Min Act: -0.1700
Data Index: 299961 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.8777. Min Act: -0.1700
Data Index: 1608185 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.7215. Min Act: -0.1700
Data Index: 2793715 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.7215. Min Act: -0.1700
Data Index: 5928090 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6902. Min Act: -0.1700
Data Index: 2959748 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6902. Min Act: -0.1700
Data Index: 4849707 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6590. Min Act: -0.1700
Data Index: 4849702 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6590. Min Act: -0.1700
Data Index: 5382947 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6590. Min Act: -0.1700
Data Index: 4849705 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6590. Min Act: -0.1700
Data Index: 718793 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6277. Min Act: -0.1700
Data Index: 3831936 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6277. Min Act: -0.1700
Data Index: 8381639 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6277. Min Act: -0.1700
Data Index: 2870017 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6277. Min Act: -0.1700
Data Index: 6186835 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.5965. Min Act: -0.1700
Data Index: 1539032 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.5652. Min Act: -0.1700
Data Index: 1102521 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0340. Min Range: -6.0340
Max Act: 5.6277. Min Act: -0.1700
Data Index: 393174 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19