Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3579. Min Range: -9.3579
Max Act: 9.3579. Min Act: -0.1700
Data Index: 5374017 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3579. Min Range: -9.3579
Max Act: 8.4204. Min Act: -0.1700
Data Index: 5607447 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.8892. Min Act: -0.1700
Data Index: 2115301 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.7642. Min Act: -0.1700
Data Index: 8097991 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.6392. Min Act: -0.1700
Data Index: 1438187 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.6704. Min Act: -0.1700
Data Index: 5382714 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.5767. Min Act: -0.1700
Data Index: 4512417 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.5767. Min Act: -0.1700
Data Index: 1697473 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.5142. Min Act: -0.1700
Data Index: 8104720 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.5142. Min Act: -0.1700
Data Index: 2201018 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.5454. Min Act: -0.1700
Data Index: 1411407 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.5142. Min Act: -0.1700
Data Index: 7118995 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.5142. Min Act: -0.1700
Data Index: 4955609 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.4829. Min Act: -0.1700
Data Index: 2115293 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.4517. Min Act: -0.1700
Data Index: 4544240 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.4517. Min Act: -0.1700
Data Index: 827188 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.4517. Min Act: -0.1700
Data Index: 914363 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.4204. Min Act: -0.1700
Data Index: 3943635 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.3892. Min Act: -0.1700
Data Index: 1642770 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3579. Min Range: -9.3579
Max Act: 7.3579. Min Act: -0.1700
Data Index: 922536 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19