Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5991 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.8608. Min Act: -0.1700
Data Index: 5554512 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7653. Min Act: -0.1700
Data Index: 1055289 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7334. Min Act: -0.1700
Data Index: 3670920 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7334. Min Act: -0.1700
Data Index: 3670931 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7334. Min Act: -0.1700
Data Index: 695911 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7334. Min Act: -0.1700
Data Index: 8674810 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7334. Min Act: -0.1700
Data Index: 1448223 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7334. Min Act: -0.1700
Data Index: 873303 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7334. Min Act: -0.1700
Data Index: 4899498 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7014. Min Act: -0.1700
Data Index: 7300431 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7014. Min Act: -0.1700
Data Index: 2677446 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7014. Min Act: -0.1700
Data Index: 7759592 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7014. Min Act: -0.1700
Data Index: 5620154 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7014. Min Act: -0.1700
Data Index: 2257507 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.7014. Min Act: -0.1700
Data Index: 3670919 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.6693. Min Act: -0.1700
Data Index: 5791327 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.6373. Min Act: -0.1700
Data Index: 4411373 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.6693. Min Act: -0.1699
Data Index: 1448216 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.6693. Min Act: -0.1700
Data Index: 614816 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8608. Min Range: -2.8608
Max Act: 2.6693. Min Act: -0.1700
Data Index: 3503628 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19