Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.8807. Min Act: -0.1700
Data Index: 734863 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.7870. Min Act: -0.1700
Data Index: 1882498 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.7870. Min Act: -0.1700
Data Index: 6188258 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.6307. Min Act: -0.1700
Data Index: 5892501 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.6307. Min Act: -0.1700
Data Index: 3400646 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.5995. Min Act: -0.1700
Data Index: 3064047 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.5370. Min Act: -0.1700
Data Index: 2153754 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.5682. Min Act: -0.1700
Data Index: 2201005 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.5370. Min Act: -0.1700
Data Index: 380938 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.5057. Min Act: -0.1700
Data Index: 2211172 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.5057. Min Act: -0.1700
Data Index: 7153459 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.4745. Min Act: -0.1700
Data Index: 5162348 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.4745. Min Act: -0.1700
Data Index: 65878 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.3807. Min Act: -0.1700
Data Index: 3860596 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.3807. Min Act: -0.1700
Data Index: 1711660 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.3495. Min Act: -0.1700
Data Index: 6595395 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.3495. Min Act: -0.1700
Data Index: 4182018 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.2870. Min Act: -0.1700
Data Index: 6547325 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.3495. Min Act: -0.1700
Data Index: 88421 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8807. Min Range: -7.8807
Max Act: 7.3182. Min Act: -0.1700
Data Index: 3864390 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19