Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4829 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0153. Min Range: -8.0153
Max Act: 8.0153. Min Act: -0.1700
Data Index: 3068764 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.9528. Min Act: -0.1700
Data Index: 3946696 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.9528. Min Act: -0.1700
Data Index: 7952849 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.9528. Min Act: -0.1700
Data Index: 5144385 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.8903. Min Act: -0.1700
Data Index: 7952847 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.8903. Min Act: -0.1700
Data Index: 7188857 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.8903. Min Act: -0.1700
Data Index: 8829390 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.8903. Min Act: -0.1700
Data Index: 4454258 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.8278. Min Act: -0.1700
Data Index: 3765176 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.7966. Min Act: -0.1700
Data Index: 1053172 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.6716. Min Act: -0.1700
Data Index: 5318143 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.7028. Min Act: -0.1700
Data Index: 4130441 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.7028. Min Act: -0.1700
Data Index: 8329046 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.7028. Min Act: -0.1700
Data Index: 8648035 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.6091. Min Act: -0.1700
Data Index: 3687967 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.6716. Min Act: -0.1700
Data Index: 5808794 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.6403. Min Act: -0.1700
Data Index: 8038102 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.6403. Min Act: -0.1700
Data Index: 1449410 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.5778. Min Act: -0.1700
Data Index: 6738906 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0153. Min Range: -8.0153
Max Act: 7.6091. Min Act: -0.1700
Data Index: 3922023 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19