Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2270 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.9800. Min Act: -0.1700
Data Index: 2509149 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.9800. Min Act: -0.1700
Data Index: 3116213 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.7925. Min Act: -0.1700
Data Index: 6793227 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7851604 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.7612. Min Act: -0.1700
Data Index: 51226 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.7300. Min Act: -0.1700
Data Index: 7758442 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6675. Min Act: -0.1700
Data Index: 75717 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6987. Min Act: -0.1700
Data Index: 7326071 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6362. Min Act: -0.1700
Data Index: 8629034 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.6362. Min Act: -0.1700
Data Index: 7600526 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5425. Min Act: -0.1700
Data Index: 7731315 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5112. Min Act: -0.1700
Data Index: 118297 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5112. Min Act: -0.1700
Data Index: 2154422 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5112. Min Act: -0.1700
Data Index: 5384445 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5112. Min Act: -0.1700
Data Index: 4000644 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5112. Min Act: -0.1700
Data Index: 267684 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4800. Min Act: -0.1700
Data Index: 2149525 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4800. Min Act: -0.1700
Data Index: 1132871 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.5112. Min Act: -0.1700
Data Index: 7226550 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9800. Min Range: -5.9800
Max Act: 5.4800. Min Act: -0.1700
Data Index: 1399748 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19