Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 871 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.2664. Min Act: -0.1700
Data Index: 5610176 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.1726. Min Act: -0.1700
Data Index: 4682807 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.1726. Min Act: -0.1700
Data Index: 4592790 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.1414. Min Act: -0.1700
Data Index: 8485295 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.1414. Min Act: -0.1700
Data Index: 1064511 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.1414. Min Act: -0.1700
Data Index: 3987647 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.1414. Min Act: -0.1700
Data Index: 685250 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.1101. Min Act: -0.1700
Data Index: 8141063 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0789. Min Act: -0.1700
Data Index: 2814160 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0789. Min Act: -0.1700
Data Index: 685253 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0789. Min Act: -0.1700
Data Index: 4538064 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0476. Min Act: -0.1700
Data Index: 5110540 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 6935006 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0476. Min Act: -0.1700
Data Index: 1123067 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 76682 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 7323774 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 808124 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2664. Min Range: -5.2664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 8262092 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2664. Min Range: -5.2664
Max Act: 4.9851. Min Act: -0.1700
Data Index: 6853549 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2664. Min Range: -5.2664
Max Act: 4.9851. Min Act: -0.1700
Data Index: 3001776 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19