Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.7867. Min Act: -0.1700
Data Index: 1132421 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.7554. Min Act: -0.1700
Data Index: 1479886 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.7242. Min Act: -0.1700
Data Index: 6510965 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.6617. Min Act: -0.1700
Data Index: 2362508 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.5679. Min Act: -0.1700
Data Index: 2004835 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4283944 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.5367. Min Act: -0.1700
Data Index: 8479549 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.5054. Min Act: -0.1700
Data Index: 5724499 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.5367. Min Act: -0.1700
Data Index: 1031285 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.5054. Min Act: -0.1700
Data Index: 5670592 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.5367. Min Act: -0.1700
Data Index: 6737830 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.4742. Min Act: -0.1700
Data Index: 5785536 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.4742. Min Act: -0.1700
Data Index: 3390707 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.4429. Min Act: -0.1700
Data Index: 3222353 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.4429. Min Act: -0.1700
Data Index: 2734459 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.3804. Min Act: -0.1700
Data Index: 5529665 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.3804. Min Act: -0.1700
Data Index: 648450 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.4117. Min Act: -0.1700
Data Index: 8412232 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.4117. Min Act: -0.1700
Data Index: 4553396 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7867. Min Range: -5.7867
Max Act: 5.4117. Min Act: -0.1700
Data Index: 2465452 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19