Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.8432. Min Act: -0.1700
Data Index: 4981057 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.7182. Min Act: -0.1700
Data Index: 4769724 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.6557. Min Act: -0.1700
Data Index: 4721697 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.5307. Min Act: -0.1700
Data Index: 3090792 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.5307. Min Act: -0.1700
Data Index: 4780124 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.4682. Min Act: -0.1700
Data Index: 7857754 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.4682. Min Act: -0.1700
Data Index: 3359350 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.4057. Min Act: -0.1700
Data Index: 1261982 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.4057. Min Act: -0.1700
Data Index: 4432917 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.4057. Min Act: -0.1700
Data Index: 6061227 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.4057. Min Act: -0.1700
Data Index: 6459239 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2807. Min Act: -0.1700
Data Index: 6738276 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2807. Min Act: -0.1700
Data Index: 5849463 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2807. Min Act: -0.1700
Data Index: 3198635 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2807. Min Act: -0.1700
Data Index: 8603779 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2807. Min Act: -0.1700
Data Index: 1896264 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2182. Min Act: -0.1700
Data Index: 5011259 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2807. Min Act: -0.1700
Data Index: 4921164 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.2182. Min Act: -0.1700
Data Index: 3819006 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8432. Min Range: -8.8432
Max Act: 8.1557. Min Act: -0.1700
Data Index: 4866652 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19