Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0186. Min Range: -6.0186
Max Act: 6.0186. Min Act: -0.1700
Data Index: 1472823 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.9873. Min Act: -0.1700
Data Index: 7626047 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.8311. Min Act: -0.1700
Data Index: 8359297 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.8311. Min Act: -0.1700
Data Index: 4137034 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.6436. Min Act: -0.1700
Data Index: 5833127 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.5498. Min Act: -0.1700
Data Index: 6743784 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.5498. Min Act: -0.1700
Data Index: 7105141 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.5186. Min Act: -0.1700
Data Index: 4137035 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4873. Min Act: -0.1700
Data Index: 168137 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.5186. Min Act: -0.1700
Data Index: 7659769 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4873. Min Act: -0.1700
Data Index: 1396510 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4561. Min Act: -0.1700
Data Index: 4079237 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4561. Min Act: -0.1700
Data Index: 7409005 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4873. Min Act: -0.1700
Data Index: 1283065 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4561. Min Act: -0.1700
Data Index: 5847371 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4873. Min Act: -0.1700
Data Index: 8138868 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4248. Min Act: -0.1700
Data Index: 7814333 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.4248. Min Act: -0.1700
Data Index: 338765 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.3936. Min Act: -0.1700
Data Index: 959288 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0186. Min Range: -6.0186
Max Act: 5.3623. Min Act: -0.1700
Data Index: 8100531 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19