Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0284. Min Range: -6.0284
Max Act: 6.0284. Min Act: -0.1700
Data Index: 6553932 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.9971. Min Act: -0.1700
Data Index: 8515315 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.9971. Min Act: -0.1700
Data Index: 6182415 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.9659. Min Act: -0.1700
Data Index: 7314123 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.9034. Min Act: -0.1700
Data Index: 2506912 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.8721. Min Act: -0.1700
Data Index: 7381239 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.8721. Min Act: -0.1700
Data Index: 4322519 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.7784. Min Act: -0.1700
Data Index: 106069 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.8096. Min Act: -0.1700
Data Index: 263436 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.7784. Min Act: -0.1700
Data Index: 2738169 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.7471. Min Act: -0.1700
Data Index: 8100663 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.7159. Min Act: -0.1700
Data Index: 6432021 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6846. Min Act: -0.1700
Data Index: 942586 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6846. Min Act: -0.1700
Data Index: 4547 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6534. Min Act: -0.1700
Data Index: 6487243 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6534. Min Act: -0.1700
Data Index: 5291512 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6846. Min Act: -0.1700
Data Index: 1916551 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6221. Min Act: -0.1700
Data Index: 184217 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6534. Min Act: -0.1700
Data Index: 3626238 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0284. Min Range: -6.0284
Max Act: 5.6221. Min Act: -0.1700
Data Index: 1969136 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19