Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5437. Min Range: -9.5437
Max Act: 9.5437. Min Act: -0.1700
Data Index: 6019835 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.6687. Min Act: -0.1700
Data Index: 3919716 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.5437. Min Act: -0.1700
Data Index: 540024 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.4812. Min Act: -0.1700
Data Index: 2265278 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.4187. Min Act: -0.1700
Data Index: 1459555 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.2312. Min Act: -0.1700
Data Index: 569012 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.2312. Min Act: -0.1700
Data Index: 3920654 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.1999. Min Act: -0.1700
Data Index: 1578890 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.1062. Min Act: -0.1700
Data Index: 2188953 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.1374. Min Act: -0.1700
Data Index: 2531166 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0749. Min Act: -0.1700
Data Index: 7207257 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0437. Min Act: -0.1700
Data Index: 5177983 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0437. Min Act: -0.1700
Data Index: 7615468 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0437. Min Act: -0.1700
Data Index: 7356703 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0437. Min Act: -0.1700
Data Index: 2780185 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0437. Min Act: -0.1700
Data Index: 118064 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0124. Min Act: -0.1700
Data Index: 7847866 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5437. Min Range: -9.5437
Max Act: 7.9812. Min Act: -0.1700
Data Index: 2127150 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5437. Min Range: -9.5437
Max Act: 8.0124. Min Act: -0.1700
Data Index: 3641319 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5437. Min Range: -9.5437
Max Act: 7.9812. Min Act: -0.1700
Data Index: 2936328 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19