Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1946 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2967. Min Range: -9.2967
Max Act: 9.2967. Min Act: -0.1700
Data Index: 6386482 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2967. Min Range: -9.2967
Max Act: 9.1717. Min Act: -0.1700
Data Index: 5295959 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2967. Min Range: -9.2967
Max Act: 9.1092. Min Act: -0.1700
Data Index: 8690618 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9842. Min Act: -0.1700
Data Index: 2179484 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9842. Min Act: -0.1700
Data Index: 2137876 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9842. Min Act: -0.1700
Data Index: 6619672 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9217. Min Act: -0.1700
Data Index: 1046 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9217. Min Act: -0.1700
Data Index: 6096278 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9217. Min Act: -0.1700
Data Index: 5939890 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9217. Min Act: -0.1700
Data Index: 7894520 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.9217. Min Act: -0.1700
Data Index: 987269 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.8592. Min Act: -0.1700
Data Index: 3668427 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.8592. Min Act: -0.1700
Data Index: 6314774 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.8592. Min Act: -0.1700
Data Index: 2706675 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.8592. Min Act: -0.1700
Data Index: 8280293 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.7967. Min Act: -0.1700
Data Index: 3446964 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.7967. Min Act: -0.1700
Data Index: 612197 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.7967. Min Act: -0.1700
Data Index: 4685323 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.7967. Min Act: -0.1700
Data Index: 3035866 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2967. Min Range: -9.2967
Max Act: 8.7967. Min Act: -0.1700
Data Index: 4748613 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19