Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5646 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1483. Min Range: -5.1483
Max Act: 5.1483. Min Act: -0.1700
Data Index: 6978895 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1483. Min Range: -5.1483
Max Act: 5.1170. Min Act: -0.1700
Data Index: 6114933 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1483. Min Range: -5.1483
Max Act: 5.0233. Min Act: -0.1700
Data Index: 3484211 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1483. Min Range: -5.1483
Max Act: 5.0233. Min Act: -0.1700
Data Index: 786430 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.9608. Min Act: -0.1700
Data Index: 2591661 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.9295. Min Act: -0.1700
Data Index: 536160 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.9295. Min Act: -0.1700
Data Index: 7804099 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.8983. Min Act: -0.1700
Data Index: 3081041 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.8358. Min Act: -0.1700
Data Index: 5300742 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.8045. Min Act: -0.1700
Data Index: 5382504 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.8045. Min Act: -0.1700
Data Index: 569118 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.8045. Min Act: -0.1700
Data Index: 6035878 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.8358. Min Act: -0.1700
Data Index: 265700 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.7420. Min Act: -0.1700
Data Index: 511148 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.7733. Min Act: -0.1700
Data Index: 4905022 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.7733. Min Act: -0.1700
Data Index: 4906198 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.7733. Min Act: -0.1700
Data Index: 7229117 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.7733. Min Act: -0.1700
Data Index: 4848177 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.7108. Min Act: -0.1700
Data Index: 7196151 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1483. Min Range: -5.1483
Max Act: 4.7108. Min Act: -0.1700
Data Index: 5070847 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19