Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1245 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.5114. Min Act: -0.1700
Data Index: 7215724 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.5114. Min Act: -0.1700
Data Index: 6012449 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.5114. Min Act: -0.1700
Data Index: 7250893 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.5114. Min Act: -0.1700
Data Index: 8213401 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.4177. Min Act: -0.1700
Data Index: 4265783 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.4177. Min Act: -0.1700
Data Index: 4265784 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.2927. Min Act: -0.1700
Data Index: 2601272 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.2614. Min Act: -0.1700
Data Index: 8818686 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.1677. Min Act: -0.1700
Data Index: 982630 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.1677. Min Act: -0.1700
Data Index: 8432899 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.1052. Min Act: -0.1700
Data Index: 7133167 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.0427. Min Act: -0.1700
Data Index: 7875600 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5114. Min Range: -7.5114
Max Act: 7.0114. Min Act: -0.1700
Data Index: 7250894 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5114. Min Range: -7.5114
Max Act: 6.9802. Min Act: -0.1700
Data Index: 5145487 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5114. Min Range: -7.5114
Max Act: 6.9489. Min Act: -0.1700
Data Index: 7325621 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5114. Min Range: -7.5114
Max Act: 6.9489. Min Act: -0.1700
Data Index: 444517 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5114. Min Range: -7.5114
Max Act: 6.9177. Min Act: -0.1700
Data Index: 4473687 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5114. Min Range: -7.5114
Max Act: 6.9489. Min Act: -0.1700
Data Index: 2311272 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5114. Min Range: -7.5114
Max Act: 6.9489. Min Act: -0.1700
Data Index: 2324184 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5114. Min Range: -7.5114
Max Act: 6.8864. Min Act: -0.1700
Data Index: 5066094 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19