Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1201. Min Range: -6.1201
Max Act: 6.1201. Min Act: -0.1700
Data Index: 7635623 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1201. Min Range: -6.1201
Max Act: 6.0263. Min Act: -0.1700
Data Index: 3819350 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9951. Min Act: -0.1700
Data Index: 1939186 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9951. Min Act: -0.1700
Data Index: 336992 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9638. Min Act: -0.1700
Data Index: 7564727 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9638. Min Act: -0.1700
Data Index: 8385317 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9638. Min Act: -0.1700
Data Index: 4778253 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9638. Min Act: -0.1700
Data Index: 5750714 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9326. Min Act: -0.1700
Data Index: 4116805 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9326. Min Act: -0.1700
Data Index: 971251 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9326. Min Act: -0.1700
Data Index: 6494467 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9326. Min Act: -0.1700
Data Index: 4925523 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9013. Min Act: -0.1700
Data Index: 6102038 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.8701. Min Act: -0.1700
Data Index: 5076972 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9013. Min Act: -0.1700
Data Index: 5334807 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9013. Min Act: -0.1700
Data Index: 2692263 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.8701. Min Act: -0.1700
Data Index: 2134088 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.8701. Min Act: -0.1700
Data Index: 1629945 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.8701. Min Act: -0.1700
Data Index: 5917624 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1201. Min Range: -6.1201
Max Act: 5.9013. Min Act: -0.1700
Data Index: 3148950 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19