Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4700 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.8376. Min Act: -0.1700
Data Index: 5486062 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.8376. Min Act: -0.1700
Data Index: 2881666 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.8063. Min Act: -0.1700
Data Index: 2746503 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.8063. Min Act: -0.1700
Data Index: 7131098 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7750. Min Act: -0.1700
Data Index: 79939 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7437. Min Act: -0.1700
Data Index: 139341 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7437. Min Act: -0.1700
Data Index: 6378833 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7437. Min Act: -0.1700
Data Index: 2744216 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7125. Min Act: -0.1700
Data Index: 1313913 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7125. Min Act: -0.1700
Data Index: 3499189 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7125. Min Act: -0.1700
Data Index: 6789167 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7125. Min Act: -0.1700
Data Index: 3162430 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.7125. Min Act: -0.1700
Data Index: 926255 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7691185 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7578212 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.6812. Min Act: -0.1700
Data Index: 8602995 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7301130 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.6812. Min Act: -0.1700
Data Index: 666703 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2118548 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8376. Min Range: -3.8376
Max Act: 3.6499. Min Act: -0.1700
Data Index: 4914398 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19