Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.9171. Min Act: -0.1700
Data Index: 7302315 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.2296. Min Act: -0.1700
Data Index: 4616913 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.1046. Min Act: -0.1700
Data Index: 5981905 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.0109. Min Act: -0.1700
Data Index: 6035805 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.9484. Min Act: -0.1700
Data Index: 5381062 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.9171. Min Act: -0.1700
Data Index: 2727992 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.9171. Min Act: -0.1700
Data Index: 2030487 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.8859. Min Act: -0.1700
Data Index: 2053727 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.8859. Min Act: -0.1700
Data Index: 7617973 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.8546. Min Act: -0.1700
Data Index: 1102155 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.8546. Min Act: -0.1700
Data Index: 3004720 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.8546. Min Act: -0.1700
Data Index: 5452622 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7921. Min Act: -0.1700
Data Index: 5457872 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7609. Min Act: -0.1700
Data Index: 6979843 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7609. Min Act: -0.1700
Data Index: 2801016 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7609. Min Act: -0.1700
Data Index: 5813725 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7609. Min Act: -0.1700
Data Index: 6455788 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7609. Min Act: -0.1700
Data Index: 1897462 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7609. Min Act: -0.1700
Data Index: 6910409 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9171. Min Range: -6.9171
Max Act: 5.7296. Min Act: -0.1700
Data Index: 4533025 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19