Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1271 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.3101. Min Act: -0.1700
Data Index: 2304209 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2630. Min Act: -0.1700
Data Index: 534413 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2630. Min Act: -0.1700
Data Index: 2512477 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2316. Min Act: -0.1700
Data Index: 6215630 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2159. Min Act: -0.1700
Data Index: 8640420 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2159. Min Act: -0.1700
Data Index: 5142410 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2002. Min Act: -0.1700
Data Index: 2003863 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1687. Min Act: -0.1700
Data Index: 6976699 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1530. Min Act: -0.1700
Data Index: 5149232 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1530. Min Act: -0.1700
Data Index: 3832495 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1530. Min Act: -0.1700
Data Index: 301068 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1530. Min Act: -0.1700
Data Index: 364173 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1530. Min Act: -0.1700
Data Index: 5874399 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1215. Min Act: -0.1700
Data Index: 8074567 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1372. Min Act: -0.1700
Data Index: 1497177 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1215. Min Act: -0.1700
Data Index: 7730753 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1215. Min Act: -0.1700
Data Index: 4490449 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1057. Min Act: -0.1700
Data Index: 8503913 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1057. Min Act: -0.1700
Data Index: 1158932 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1057. Min Act: -0.1700
Data Index: 7087602 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19