Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2220 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.5137. Min Act: -0.1700
Data Index: 2580905 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.3887. Min Act: -0.1700
Data Index: 1994687 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.3262. Min Act: -0.1700
Data Index: 6762620 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.2637. Min Act: -0.1700
Data Index: 1126911 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.2012. Min Act: -0.1700
Data Index: 5638379 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.1387. Min Act: -0.1700
Data Index: 955744 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0762. Min Act: -0.1700
Data Index: 4968118 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0762. Min Act: -0.1700
Data Index: 1060314 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0762. Min Act: -0.1700
Data Index: 3385865 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0762. Min Act: -0.1700
Data Index: 5007665 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0762. Min Act: -0.1700
Data Index: 2481458 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0762. Min Act: -0.1700
Data Index: 4258989 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0762. Min Act: -0.1700
Data Index: 7139979 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0137. Min Act: -0.1700
Data Index: 2374888 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0137. Min Act: -0.1700
Data Index: 3277928 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0137. Min Act: -0.1700
Data Index: 5614324 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0137. Min Act: -0.1700
Data Index: 367302 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5137. Min Range: -9.5137
Max Act: 8.9512. Min Act: -0.1700
Data Index: 3615649 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0137. Min Act: -0.1700
Data Index: 1798915 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5137. Min Range: -9.5137
Max Act: 9.0137. Min Act: -0.1700
Data Index: 315026 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19