Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4689 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9661. Min Act: -0.1700
Data Index: 4167244 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.9036. Min Act: -0.1700
Data Index: 2729331 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8723. Min Act: -0.1700
Data Index: 2666214 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8411. Min Act: -0.1700
Data Index: 5806244 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.8098. Min Act: -0.1700
Data Index: 5993142 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7785. Min Act: -0.1700
Data Index: 8809227 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7629. Min Act: -0.1700
Data Index: 4145706 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7629. Min Act: -0.1700
Data Index: 7208105 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7629. Min Act: -0.1700
Data Index: 1072431 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7472. Min Act: -0.1700
Data Index: 487666 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7472. Min Act: -0.1700
Data Index: 1975831 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7472. Min Act: -0.1700
Data Index: 1441553 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7316. Min Act: -0.1700
Data Index: 3169520 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.7160. Min Act: -0.1700
Data Index: 4656330 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.6847. Min Act: -0.1700
Data Index: 884077 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.6847. Min Act: -0.1700
Data Index: 1333957 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.6847. Min Act: -0.1700
Data Index: 6064085 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.6690. Min Act: -0.1700
Data Index: 1187321 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.6534. Min Act: -0.1700
Data Index: 1770521 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9661. Min Range: -3.9661
Max Act: 3.6690. Min Act: -0.1700
Data Index: 152526 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19