Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8129. Min Range: -7.8129
Max Act: 7.8129. Min Act: -0.1700
Data Index: 5076683 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8129. Min Range: -7.8129
Max Act: 7.5942. Min Act: -0.1700
Data Index: 7085037 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8129. Min Range: -7.8129
Max Act: 7.3442. Min Act: -0.1700
Data Index: 2492007 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.9692. Min Act: -0.1700
Data Index: 6818770 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8129. Min Range: -7.8129
Max Act: 7.0004. Min Act: -0.1700
Data Index: 5655506 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.9692. Min Act: -0.1700
Data Index: 7824043 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.9692. Min Act: -0.1700
Data Index: 2715852 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.9692. Min Act: -0.1700
Data Index: 3903808 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.9379. Min Act: -0.1700
Data Index: 6433513 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.9379. Min Act: -0.1700
Data Index: 6938586 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.9067. Min Act: -0.1700
Data Index: 2921744 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.8442. Min Act: -0.1700
Data Index: 8604799 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.8754. Min Act: -0.1700
Data Index: 856386 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.8442. Min Act: -0.1700
Data Index: 6253703 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.8442. Min Act: -0.1700
Data Index: 182 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.8442. Min Act: -0.1700
Data Index: 7913882 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.8442. Min Act: -0.1700
Data Index: 3103895 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.7504. Min Act: -0.1700
Data Index: 6753597 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.7192. Min Act: -0.1700
Data Index: 14677 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8129. Min Range: -7.8129
Max Act: 6.7192. Min Act: -0.1700
Data Index: 3386566 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19