Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 694 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3762. Min Range: -9.3762
Max Act: 9.3762. Min Act: -0.1700
Data Index: 179856 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.8137. Min Act: -0.1700
Data Index: 2660952 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.7512. Min Act: -0.1700
Data Index: 8722044 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.6887. Min Act: -0.1700
Data Index: 2618705 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.6887. Min Act: -0.1700
Data Index: 3325056 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.6262. Min Act: -0.1700
Data Index: 3222733 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.6262. Min Act: -0.1700
Data Index: 8831672 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5637. Min Act: -0.1700
Data Index: 7873172 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5637. Min Act: -0.1700
Data Index: 7004636 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5637. Min Act: -0.1700
Data Index: 4139043 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5637. Min Act: -0.1700
Data Index: 4627955 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5637. Min Act: -0.1700
Data Index: 4319319 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5637. Min Act: -0.1700
Data Index: 3152431 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5012. Min Act: -0.1700
Data Index: 3870723 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5012. Min Act: -0.1700
Data Index: 317327 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5012. Min Act: -0.1700
Data Index: 907286 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.4387. Min Act: -0.1700
Data Index: 1132988 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.4387. Min Act: -0.1700
Data Index: 1438859 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.4387. Min Act: -0.1700
Data Index: 5884942 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3762. Min Range: -9.3762
Max Act: 8.5012. Min Act: -0.1700
Data Index: 2046114 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19