Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.8970. Min Act: -0.1700
Data Index: 2986675 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.8033. Min Act: -0.1700
Data Index: 7916038 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.6158. Min Act: -0.1700
Data Index: 8631142 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.6470. Min Act: -0.1700
Data Index: 2177849 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.6158. Min Act: -0.1700
Data Index: 5766897 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.5533. Min Act: -0.1700
Data Index: 7706298 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.5845. Min Act: -0.1700
Data Index: 8519020 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.5220. Min Act: -0.1700
Data Index: 1155089 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.5220. Min Act: -0.1700
Data Index: 8568716 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.4908. Min Act: -0.1700
Data Index: 3438457 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.4283. Min Act: -0.1700
Data Index: 7083385 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.4283. Min Act: -0.1700
Data Index: 8385782 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3970. Min Act: -0.1700
Data Index: 4631965 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3970. Min Act: -0.1700
Data Index: 2556445 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3970. Min Act: -0.1700
Data Index: 788321 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3658. Min Act: -0.1700
Data Index: 65998 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3658. Min Act: -0.1700
Data Index: 1706275 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3970. Min Act: -0.1700
Data Index: 4615492 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3658. Min Act: -0.1700
Data Index: 5871437 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8970. Min Range: -4.8970
Max Act: 4.3658. Min Act: -0.1700
Data Index: 6362503 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19