Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6394 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.8252. Min Act: -0.1700
Data Index: 5951384 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.4339. Min Act: -0.1700
Data Index: 4009710 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.3712. Min Act: -0.1700
Data Index: 4811961 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.3555. Min Act: -0.1700
Data Index: 1312899 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.3241. Min Act: -0.1700
Data Index: 3371346 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.3084. Min Act: -0.1700
Data Index: 938136 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.2456. Min Act: -0.1700
Data Index: 2602003 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.2456. Min Act: -0.1700
Data Index: 8510710 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.2299. Min Act: -0.1700
Data Index: 4614879 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.2142. Min Act: -0.1700
Data Index: 3785998 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1827. Min Act: -0.1700
Data Index: 2753103 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1827. Min Act: -0.1700
Data Index: 93087 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1670. Min Act: -0.1700
Data Index: 4753400 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1670. Min Act: -0.1700
Data Index: 816913 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1670. Min Act: -0.1700
Data Index: 4862940 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1670. Min Act: -0.1700
Data Index: 3597324 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1512. Min Act: -0.1700
Data Index: 5636902 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1355. Min Act: -0.1700
Data Index: 7304728 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1355. Min Act: -0.1700
Data Index: 389828 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8252. Min Range: -3.8252
Max Act: 3.1355. Min Act: -0.1700
Data Index: 2250745 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19