Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.4440. Min Act: -0.1700
Data Index: 4825946 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.4440. Min Act: -0.1700
Data Index: 283555 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2878. Min Act: -0.1700
Data Index: 8177938 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2878. Min Act: -0.1700
Data Index: 6754191 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2878. Min Act: -0.1700
Data Index: 6687750 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2565. Min Act: -0.1700
Data Index: 2290920 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2878. Min Act: -0.1700
Data Index: 6071827 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2565. Min Act: -0.1700
Data Index: 5142563 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2565. Min Act: -0.1700
Data Index: 7707993 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2565. Min Act: -0.1700
Data Index: 6128625 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2252. Min Act: -0.1700
Data Index: 5225788 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2252. Min Act: -0.1700
Data Index: 7678371 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2252. Min Act: -0.1700
Data Index: 7402801 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.1940. Min Act: -0.1700
Data Index: 1234748 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2252. Min Act: -0.1700
Data Index: 381111 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.2252. Min Act: -0.1700
Data Index: 933580 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.1940. Min Act: -0.1700
Data Index: 7325770 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.1940. Min Act: -0.1700
Data Index: 570267 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.1940. Min Act: -0.1700
Data Index: 5499970 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4440. Min Range: -4.4440
Max Act: 4.1940. Min Act: -0.1700
Data Index: 6004052 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19