Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8366. Min Range: -6.8366
Max Act: 6.8366. Min Act: -0.1700
Data Index: 1671283 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8366. Min Range: -6.8366
Max Act: 6.1491. Min Act: -0.1700
Data Index: 1970794 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.9929. Min Act: -0.1700
Data Index: 5575551 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.9616. Min Act: -0.1700
Data Index: 4045335 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 1889304 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.9304. Min Act: -0.1700
Data Index: 5840 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.9304. Min Act: -0.1700
Data Index: 6070057 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.9304. Min Act: -0.1700
Data Index: 5285744 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.9304. Min Act: -0.1700
Data Index: 4082721 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 1143814 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8679. Min Act: -0.1700
Data Index: 2265664 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 6743692 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 47011 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 7649539 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 7936513 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8679. Min Act: -0.1700
Data Index: 3011526 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 4635576 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8366. Min Act: -0.1700
Data Index: 7217065 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8679. Min Act: -0.1700
Data Index: 5597024 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8366. Min Range: -6.8366
Max Act: 5.8366. Min Act: -0.1700
Data Index: 5291105 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19