Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2163 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0002. Min Range: -6.0002
Max Act: 6.0002. Min Act: -0.1700
Data Index: 7396382 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.9377. Min Act: -0.1700
Data Index: 6438393 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.9689. Min Act: -0.1700
Data Index: 3987014 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8752. Min Act: -0.1700
Data Index: 5604549 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8752. Min Act: -0.1700
Data Index: 7126761 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8752. Min Act: -0.1700
Data Index: 6438394 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8752. Min Act: -0.1700
Data Index: 4601012 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8752. Min Act: -0.1700
Data Index: 1801475 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8439. Min Act: -0.1700
Data Index: 8322641 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8439. Min Act: -0.1700
Data Index: 6738829 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.8127. Min Act: -0.1700
Data Index: 5253985 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.7814. Min Act: -0.1700
Data Index: 5100557 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.7502. Min Act: -0.1700
Data Index: 2161341 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.7502. Min Act: -0.1700
Data Index: 5917386 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.7189. Min Act: -0.1700
Data Index: 570127 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.7189. Min Act: -0.1700
Data Index: 7004513 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.6877. Min Act: -0.1700
Data Index: 6472176 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.6877. Min Act: -0.1700
Data Index: 6738828 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.6877. Min Act: -0.1700
Data Index: 3987017 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0002. Min Range: -6.0002
Max Act: 5.6252. Min Act: -0.1700
Data Index: 2795080 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19