Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1396 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.7198. Min Act: -0.1700
Data Index: 2995925 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.6885. Min Act: -0.1700
Data Index: 5393702 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.6729. Min Act: -0.1700
Data Index: 6785037 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.5633. Min Act: -0.1700
Data Index: 25384 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.5320. Min Act: -0.1700
Data Index: 5992733 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4850. Min Act: -0.1700
Data Index: 4841166 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.5007. Min Act: -0.1700
Data Index: 5249830 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4850. Min Act: -0.1700
Data Index: 7908898 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4537. Min Act: -0.1700
Data Index: 6026862 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4537. Min Act: -0.1700
Data Index: 6030341 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4380. Min Act: -0.1700
Data Index: 5900601 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4380. Min Act: -0.1700
Data Index: 8021724 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4224. Min Act: -0.1700
Data Index: 1875955 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4067. Min Act: -0.1700
Data Index: 149510 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4224. Min Act: -0.1700
Data Index: 7046896 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.4224. Min Act: -0.1700
Data Index: 2063911 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.3910. Min Act: -0.1700
Data Index: 1674991 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.3753. Min Act: -0.1700
Data Index: 1140894 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.3753. Min Act: -0.1700
Data Index: 2229467 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7198. Min Range: -3.7198
Max Act: 3.3910. Min Act: -0.1700
Data Index: 5045151 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19