Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4499 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3870. Min Range: -8.3870
Max Act: 8.3870. Min Act: -0.1700
Data Index: 5440369 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3870. Min Range: -8.3870
Max Act: 8.0120. Min Act: -0.1700
Data Index: 5046826 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3870. Min Range: -8.3870
Max Act: 8.0120. Min Act: -0.1700
Data Index: 7230700 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.7620. Min Act: -0.1700
Data Index: 254212 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.6995. Min Act: -0.1700
Data Index: 5573817 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.5745. Min Act: -0.1700
Data Index: 1958851 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.4495. Min Act: -0.1700
Data Index: 3548406 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.5120. Min Act: -0.1700
Data Index: 989008 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.5120. Min Act: -0.1700
Data Index: 579566 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.4495. Min Act: -0.1700
Data Index: 4751745 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.3870. Min Act: -0.1700
Data Index: 1687279 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.3557. Min Act: -0.1700
Data Index: 5919711 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.3870. Min Act: -0.1700
Data Index: 3418595 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.3557. Min Act: -0.1700
Data Index: 56166 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.3870. Min Act: -0.1700
Data Index: 1521989 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.3557. Min Act: -0.1700
Data Index: 7617330 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.2932. Min Act: -0.1700
Data Index: 977719 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.3245. Min Act: -0.1700
Data Index: 773178 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.2932. Min Act: -0.1700
Data Index: 5550338 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3870. Min Range: -8.3870
Max Act: 7.2932. Min Act: -0.1700
Data Index: 5246850 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19