Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1224 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4037. Min Range: -8.4037
Max Act: 8.4037. Min Act: -0.1700
Data Index: 931523 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4037. Min Range: -8.4037
Max Act: 8.1537. Min Act: -0.1700
Data Index: 8429463 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.9974. Min Act: -0.1700
Data Index: 6233109 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.9662. Min Act: -0.1700
Data Index: 1990423 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.8412. Min Act: -0.1700
Data Index: 1233527 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.8099. Min Act: -0.1700
Data Index: 2190131 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.7787. Min Act: -0.1700
Data Index: 4564925 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.7787. Min Act: -0.1700
Data Index: 1873146 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.7474. Min Act: -0.1700
Data Index: 6503630 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.7162. Min Act: -0.1700
Data Index: 368686 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.7162. Min Act: -0.1700
Data Index: 2007438 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 5475853 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.7162. Min Act: -0.1700
Data Index: 686518 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6849. Min Act: -0.1700
Data Index: 3709362 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 4962600 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 2797541 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 599543 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6224. Min Act: -0.1700
Data Index: 6732103 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6537. Min Act: -0.1700
Data Index: 3589703 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4037. Min Range: -8.4037
Max Act: 7.6224. Min Act: -0.1700
Data Index: 701529 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19