Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3327 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.7055. Min Act: -0.1700
Data Index: 7791795 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.5492. Min Act: -0.1700
Data Index: 6635210 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.3930. Min Act: -0.1700
Data Index: 6792270 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.3617. Min Act: -0.1700
Data Index: 533744 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2992. Min Act: -0.1700
Data Index: 1893227 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2680. Min Act: -0.1700
Data Index: 5129510 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2992. Min Act: -0.1700
Data Index: 484448 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2992. Min Act: -0.1700
Data Index: 2336675 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2680. Min Act: -0.1700
Data Index: 5906945 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2680. Min Act: -0.1700
Data Index: 3194749 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2680. Min Act: -0.1700
Data Index: 3523039 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2367. Min Act: -0.1700
Data Index: 259101 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2367. Min Act: -0.1700
Data Index: 4301296 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2680. Min Act: -0.1700
Data Index: 8820703 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2367. Min Act: -0.1700
Data Index: 4053600 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.2055. Min Act: -0.1700
Data Index: 8730199 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.1742. Min Act: -0.1700
Data Index: 7467538 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.1742. Min Act: -0.1700
Data Index: 2141750 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.1742. Min Act: -0.1700
Data Index: 4161037 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7055. Min Range: -5.7055
Max Act: 5.1742. Min Act: -0.1700
Data Index: 5076286 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19