Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.2992. Min Act: -0.1700
Data Index: 720168 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.2367. Min Act: -0.1700
Data Index: 2152371 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.2367. Min Act: -0.1700
Data Index: 3888925 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.2367. Min Act: -0.1700
Data Index: 1263767 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.2054. Min Act: -0.1700
Data Index: 8335786 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.2054. Min Act: -0.1700
Data Index: 1320086 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.2054. Min Act: -0.1700
Data Index: 5339825 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1742. Min Act: -0.1700
Data Index: 4814163 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1742. Min Act: -0.1700
Data Index: 1509247 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1429. Min Act: -0.1700
Data Index: 560022 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1429. Min Act: -0.1700
Data Index: 5099643 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1742. Min Act: -0.1700
Data Index: 6225118 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1116. Min Act: -0.1700
Data Index: 1649331 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1116. Min Act: -0.1700
Data Index: 6061686 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1116. Min Act: -0.1700
Data Index: 5465671 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1116. Min Act: -0.1700
Data Index: 6273766 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.1429. Min Act: -0.1700
Data Index: 8424879 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.0804. Min Act: -0.1700
Data Index: 5271533 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.0804. Min Act: -0.1700
Data Index: 7492478 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2992. Min Range: -4.2992
Max Act: 4.0491. Min Act: -0.1700
Data Index: 7143208 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19