Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5206 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0951. Min Range: -6.0951
Max Act: 6.0951. Min Act: -0.1700
Data Index: 7209353 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.9389. Min Act: -0.1700
Data Index: 551801 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.9076. Min Act: -0.1700
Data Index: 2981895 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.9389. Min Act: -0.1700
Data Index: 3891905 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.8451. Min Act: -0.1700
Data Index: 7365383 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7826. Min Act: -0.1700
Data Index: 1773114 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7826. Min Act: -0.1700
Data Index: 1026406 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7826. Min Act: -0.1700
Data Index: 7882621 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7514. Min Act: -0.1700
Data Index: 6157627 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7514. Min Act: -0.1700
Data Index: 3544415 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7201. Min Act: -0.1700
Data Index: 6088210 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7201. Min Act: -0.1700
Data Index: 727372 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.7201. Min Act: -0.1700
Data Index: 1465175 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.6889. Min Act: -0.1700
Data Index: 3169803 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.6576. Min Act: -0.1700
Data Index: 6236191 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.6889. Min Act: -0.1700
Data Index: 1325531 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.6576. Min Act: -0.1700
Data Index: 4872834 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.6576. Min Act: -0.1700
Data Index: 5389753 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.6576. Min Act: -0.1700
Data Index: 1411925 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0951. Min Range: -6.0951
Max Act: 5.6576. Min Act: -0.1700
Data Index: 820587 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19