Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.5492. Min Act: -0.1700
Data Index: 7277269 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.3617. Min Act: -0.1700
Data Index: 6218000 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2367. Min Act: -0.1700
Data Index: 3961450 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.2055. Min Act: -0.1700
Data Index: 4785575 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.0492. Min Act: -0.1700
Data Index: 8201140 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.0180. Min Act: -0.1700
Data Index: 6328693 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5492. Min Range: -5.5492
Max Act: 5.0180. Min Act: -0.1700
Data Index: 6244566 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.9867. Min Act: -0.1700
Data Index: 2548556 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.9555. Min Act: -0.1700
Data Index: 2932291 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.9555. Min Act: -0.1700
Data Index: 1182826 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.9867. Min Act: -0.1700
Data Index: 5310830 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.9555. Min Act: -0.1700
Data Index: 8398116 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8930. Min Act: -0.1700
Data Index: 3730426 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8930. Min Act: -0.1700
Data Index: 2524114 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8930. Min Act: -0.1700
Data Index: 6039596 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8617. Min Act: -0.1700
Data Index: 2415595 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8305. Min Act: -0.1700
Data Index: 4186695 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8617. Min Act: -0.1700
Data Index: 3493597 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8617. Min Act: -0.1700
Data Index: 6671750 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5492. Min Range: -5.5492
Max Act: 4.8930. Min Act: -0.1700
Data Index: 2616898 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19