Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0686. Min Range: -6.0686
Max Act: 6.0686. Min Act: -0.1700
Data Index: 1975571 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0686. Min Range: -6.0686
Max Act: 6.0373. Min Act: -0.1700
Data Index: 556217 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0686. Min Range: -6.0686
Max Act: 6.0061. Min Act: -0.1700
Data Index: 8615856 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0686. Min Range: -6.0686
Max Act: 6.0061. Min Act: -0.1700
Data Index: 8492292 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.9748. Min Act: -0.1700
Data Index: 4861963 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.9436. Min Act: -0.1700
Data Index: 1929687 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.9123. Min Act: -0.1700
Data Index: 2631945 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.9123. Min Act: -0.1700
Data Index: 6771826 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.9123. Min Act: -0.1700
Data Index: 3084335 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.8811. Min Act: -0.1700
Data Index: 4218963 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.8811. Min Act: -0.1700
Data Index: 7707654 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.8811. Min Act: -0.1700
Data Index: 2140658 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.8498. Min Act: -0.1700
Data Index: 2356124 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.8186. Min Act: -0.1700
Data Index: 7873683 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.7873. Min Act: -0.1700
Data Index: 7873685 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.8186. Min Act: -0.1700
Data Index: 5038382 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.7873. Min Act: -0.1700
Data Index: 2356123 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.7561. Min Act: -0.1700
Data Index: 1629692 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.7561. Min Act: -0.1700
Data Index: 6659315 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0686. Min Range: -6.0686
Max Act: 5.7561. Min Act: -0.1700
Data Index: 6739249 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19