Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1984. Min Range: -8.1984
Max Act: 8.1984. Min Act: -0.1700
Data Index: 4152809 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1984. Min Range: -8.1984
Max Act: 8.0109. Min Act: -0.1700
Data Index: 7156387 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.9484. Min Act: -0.1700
Data Index: 3774741 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.8234. Min Act: -0.1700
Data Index: 7958335 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.8859. Min Act: -0.1700
Data Index: 5517500 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.8859. Min Act: -0.1700
Data Index: 3265555 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.8234. Min Act: -0.1700
Data Index: 4344331 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.8234. Min Act: -0.1700
Data Index: 258106 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.8234. Min Act: -0.1700
Data Index: 301430 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.8234. Min Act: -0.1700
Data Index: 5810333 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 5938822 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 3921683 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 7730290 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 1837230 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 3992023 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 1864026 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 7904606 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 4587538 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 2840540 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1984. Min Range: -8.1984
Max Act: 7.7609. Min Act: -0.1700
Data Index: 338539 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19