Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.9884. Min Act: -0.1700
Data Index: 6540602 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.8634. Min Act: -0.1700
Data Index: 454002 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.8321. Min Act: -0.1700
Data Index: 2840513 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.7696. Min Act: -0.1700
Data Index: 5226187 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.7384. Min Act: -0.1700
Data Index: 2071595 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.7071. Min Act: -0.1700
Data Index: 3767572 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.6759. Min Act: -0.1700
Data Index: 1908311 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.6759. Min Act: -0.1700
Data Index: 4876779 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.6446. Min Act: -0.1700
Data Index: 4756461 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.6446. Min Act: -0.1700
Data Index: 6107056 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.6446. Min Act: -0.1700
Data Index: 3979822 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5821. Min Act: -0.1700
Data Index: 4257929 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5821. Min Act: -0.1700
Data Index: 2189165 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5821. Min Act: -0.1700
Data Index: 4799301 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5821. Min Act: -0.1700
Data Index: 6570151 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5821. Min Act: -0.1700
Data Index: 3337257 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5821. Min Act: -0.1700
Data Index: 2094010 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5509. Min Act: -0.1700
Data Index: 6228747 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5509. Min Act: -0.1700
Data Index: 3480734 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9884. Min Range: -6.9884
Max Act: 6.5509. Min Act: -0.1700
Data Index: 6448221 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19