Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4478 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1509. Min Range: -5.1509
Max Act: 5.1509. Min Act: -0.1700
Data Index: 4623330 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1509. Min Range: -5.1509
Max Act: 5.1197. Min Act: -0.1700
Data Index: 555285 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9947. Min Act: -0.1700
Data Index: 4614563 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9634. Min Act: -0.1700
Data Index: 904001 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9634. Min Act: -0.1700
Data Index: 7814049 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9322. Min Act: -0.1700
Data Index: 555283 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9322. Min Act: -0.1700
Data Index: 8506114 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9322. Min Act: -0.1700
Data Index: 5213972 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9322. Min Act: -0.1700
Data Index: 4089128 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8697. Min Act: -0.1700
Data Index: 4894183 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8697. Min Act: -0.1700
Data Index: 7814050 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8697. Min Act: -0.1700
Data Index: 5458418 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 2656840 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 240356 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8072. Min Act: -0.1700
Data Index: 2847774 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 7814051 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 6365372 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 5321010 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 8380166 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 3564555 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19