Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0455. Min Range: -6.0455
Max Act: 6.0455. Min Act: -0.1700
Data Index: 4681774 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.7643. Min Act: -0.1700
Data Index: 754392 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.7330. Min Act: -0.1700
Data Index: 8644695 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.6393. Min Act: -0.1700
Data Index: 5232296 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.6393. Min Act: -0.1700
Data Index: 6162506 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.6080. Min Act: -0.1700
Data Index: 1969232 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.6080. Min Act: -0.1700
Data Index: 2860220 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.6080. Min Act: -0.1700
Data Index: 5885814 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.5143. Min Act: -0.1700
Data Index: 7477427 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.5143. Min Act: -0.1700
Data Index: 7644915 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.4830. Min Act: -0.1700
Data Index: 7244122 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.3893. Min Act: -0.1700
Data Index: 2184470 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.4205. Min Act: -0.1700
Data Index: 3223786 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.3893. Min Act: -0.1700
Data Index: 2258268 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.3893. Min Act: -0.1700
Data Index: 3004843 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.3893. Min Act: -0.1700
Data Index: 3223788 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.3893. Min Act: -0.1700
Data Index: 4732294 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.3580. Min Act: -0.1700
Data Index: 6809862 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.4205. Min Act: -0.1700
Data Index: 7100793 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0455. Min Range: -6.0455
Max Act: 5.3580. Min Act: -0.1700
Data Index: 169263 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19