Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1770 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 5336337 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.2269. Min Act: -0.1700
Data Index: 3256295 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1644. Min Act: -0.1700
Data Index: 3582393 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.1332. Min Act: -0.1700
Data Index: 5550414 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 5979366 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 3921619 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0082. Min Act: -0.1700
Data Index: 2591996 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2894. Min Range: -5.2894
Max Act: 5.0394. Min Act: -0.1700
Data Index: 3427290 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9769. Min Act: -0.1700
Data Index: 3179016 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9769. Min Act: -0.1700
Data Index: 7431916 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 758075 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9457. Min Act: -0.1700
Data Index: 3256291 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 3989068 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.9144. Min Act: -0.1700
Data Index: 1994883 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 5181996 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8832. Min Act: -0.1700
Data Index: 7055248 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8832. Min Act: -0.1700
Data Index: 252925 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8832. Min Act: -0.1700
Data Index: 4180212 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8519. Min Act: -0.1700
Data Index: 4880005 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2894. Min Range: -5.2894
Max Act: 4.8207. Min Act: -0.1700
Data Index: 5402778 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19