Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1104 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3017. Min Range: -6.3017
Max Act: 6.3017. Min Act: -0.1700
Data Index: 6774437 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3017. Min Range: -6.3017
Max Act: 6.2705. Min Act: -0.1700
Data Index: 168129 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3017. Min Range: -6.3017
Max Act: 6.2392. Min Act: -0.1700
Data Index: 5317745 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3017. Min Range: -6.3017
Max Act: 6.2392. Min Act: -0.1700
Data Index: 6616746 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3017. Min Range: -6.3017
Max Act: 6.1142. Min Act: -0.1700
Data Index: 6563873 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3017. Min Range: -6.3017
Max Act: 6.0517. Min Act: -0.1700
Data Index: 6851820 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3017. Min Range: -6.3017
Max Act: 6.0205. Min Act: -0.1700
Data Index: 6991178 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.9892. Min Act: -0.1700
Data Index: 2503519 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.9892. Min Act: -0.1700
Data Index: 2814216 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.9892. Min Act: -0.1700
Data Index: 3246295 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.9580. Min Act: -0.1700
Data Index: 5318983 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.9267. Min Act: -0.1700
Data Index: 5052623 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8955. Min Act: -0.1700
Data Index: 429592 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8955. Min Act: -0.1700
Data Index: 550992 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8642. Min Act: -0.1700
Data Index: 3720273 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8642. Min Act: -0.1700
Data Index: 6426142 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8330. Min Act: -0.1700
Data Index: 4297507 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8330. Min Act: -0.1700
Data Index: 6290141 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8642. Min Act: -0.1700
Data Index: 8683683 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3017. Min Range: -6.3017
Max Act: 5.8330. Min Act: -0.1700
Data Index: 2214637 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19