Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.6751. Min Act: -0.1700
Data Index: 8072935 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.4876. Min Act: -0.1700
Data Index: 3521609 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.3001. Min Act: -0.1700
Data Index: 3523768 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.2689. Min Act: -0.1700
Data Index: 2686941 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.2376. Min Act: -0.1700
Data Index: 7313726 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.1751. Min Act: -0.1700
Data Index: 7459850 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.1439. Min Act: -0.1700
Data Index: 5175708 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.1126. Min Act: -0.1700
Data Index: 6017493 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0814. Min Act: -0.1700
Data Index: 3939686 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0814. Min Act: -0.1700
Data Index: 750919 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0501. Min Act: -0.1700
Data Index: 5090885 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0189. Min Act: -0.1700
Data Index: 3442316 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0501. Min Act: -0.1700
Data Index: 5683333 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0501. Min Act: -0.1700
Data Index: 3354759 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0501. Min Act: -0.1700
Data Index: 1588631 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0189. Min Act: -0.1700
Data Index: 7596877 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0189. Min Act: -0.1700
Data Index: 3581354 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6751. Min Range: -6.6751
Max Act: 6.0189. Min Act: -0.1700
Data Index: 5070908 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6751. Min Range: -6.6751
Max Act: 5.9876. Min Act: -0.1700
Data Index: 4409844 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6751. Min Range: -6.6751
Max Act: 5.9876. Min Act: -0.1700
Data Index: 2142490 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19