Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4745 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.5015. Min Act: -0.1700
Data Index: 1212163 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.4390. Min Act: -0.1700
Data Index: 1212152 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.3452. Min Act: -0.1700
Data Index: 6739018 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.2202. Min Act: -0.1700
Data Index: 7040477 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.2827. Min Act: -0.1700
Data Index: 2158870 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.2202. Min Act: -0.1700
Data Index: 6608764 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.2202. Min Act: -0.1700
Data Index: 2560692 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.1577. Min Act: -0.1700
Data Index: 4519229 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.1890. Min Act: -0.1700
Data Index: 8281117 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.0952. Min Act: -0.1700
Data Index: 1484393 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.0327. Min Act: -0.1700
Data Index: 2687299 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.0327. Min Act: -0.1700
Data Index: 4519232 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.0015. Min Act: -0.1700
Data Index: 5046458 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.0327. Min Act: -0.1700
Data Index: 4519231 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5015. Min Range: -5.5015
Max Act: 5.0015. Min Act: -0.1700
Data Index: 4519230 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5015. Min Range: -5.5015
Max Act: 4.9702. Min Act: -0.1700
Data Index: 4718245 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5015. Min Range: -5.5015
Max Act: 4.9702. Min Act: -0.1700
Data Index: 3830058 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5015. Min Range: -5.5015
Max Act: 4.9702. Min Act: -0.1700
Data Index: 3939807 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5015. Min Range: -5.5015
Max Act: 4.9077. Min Act: -0.1700
Data Index: 6418614 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5015. Min Range: -5.5015
Max Act: 4.9390. Min Act: -0.1700
Data Index: 5132629 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19