Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.5650. Min Act: -0.1700
Data Index: 2854731 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.2213. Min Act: -0.1700
Data Index: 3147454 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.2525. Min Act: -0.1700
Data Index: 4954227 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.2213. Min Act: -0.1700
Data Index: 7403551 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.1900. Min Act: -0.1700
Data Index: 7457410 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.1900. Min Act: -0.1700
Data Index: 7701034 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.1588. Min Act: -0.1700
Data Index: 8635588 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0963. Min Act: -0.1700
Data Index: 4230724 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0963. Min Act: -0.1700
Data Index: 5337445 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0650. Min Act: -0.1700
Data Index: 6941903 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0650. Min Act: -0.1700
Data Index: 332410 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0338. Min Act: -0.1700
Data Index: 4229670 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0025. Min Act: -0.1700
Data Index: 2931064 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0025. Min Act: -0.1700
Data Index: 4807347 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0025. Min Act: -0.1700
Data Index: 1853439 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5650. Min Range: -6.5650
Max Act: 6.0338. Min Act: -0.1700
Data Index: 360012 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5650. Min Range: -6.5650
Max Act: 5.9713. Min Act: -0.1700
Data Index: 3923520 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5650. Min Range: -6.5650
Max Act: 5.9400. Min Act: -0.1700
Data Index: 8812371 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5650. Min Range: -6.5650
Max Act: 5.9713. Min Act: -0.1700
Data Index: 929211 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5650. Min Range: -6.5650
Max Act: 5.9400. Min Act: -0.1700
Data Index: 4732173 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19