Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1892. Min Range: -8.1892
Max Act: 8.1892. Min Act: -0.1700
Data Index: 376713 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1892. Min Range: -8.1892
Max Act: 8.0642. Min Act: -0.1700
Data Index: 4251142 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1892. Min Range: -8.1892
Max Act: 8.0642. Min Act: -0.1700
Data Index: 4463008 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.9392. Min Act: -0.1700
Data Index: 3713936 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.7517. Min Act: -0.1700
Data Index: 3854884 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.7517. Min Act: -0.1700
Data Index: 1241820 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.6892. Min Act: -0.1700
Data Index: 42594 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.6892. Min Act: -0.1700
Data Index: 4487471 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.5642. Min Act: -0.1700
Data Index: 2104142 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.6267. Min Act: -0.1700
Data Index: 2118534 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.5642. Min Act: -0.1700
Data Index: 3370000 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.6267. Min Act: -0.1700
Data Index: 2163221 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.6267. Min Act: -0.1700
Data Index: 2941912 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.6267. Min Act: -0.1700
Data Index: 1674873 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.5642. Min Act: -0.1700
Data Index: 942681 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.6267. Min Act: -0.1700
Data Index: 3403154 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.5017. Min Act: -0.1700
Data Index: 4969429 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.5017. Min Act: -0.1700
Data Index: 7305124 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.4705. Min Act: -0.1700
Data Index: 3082429 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1892. Min Range: -8.1892
Max Act: 7.4705. Min Act: -0.1700
Data Index: 664752 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19