Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5413 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1915. Min Act: -0.1700
Data Index: 948645 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1915. Min Act: -0.1700
Data Index: 2299621 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1915. Min Act: -0.1700
Data Index: 5337565 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1602. Min Act: -0.1700
Data Index: 530669 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1915. Min Act: -0.1700
Data Index: 8134829 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1602. Min Act: -0.1700
Data Index: 8188456 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 5124363 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.0977. Min Act: -0.1700
Data Index: 2881237 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 4759393 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 8822909 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 3851950 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 3489292 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 3077034 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 2633710 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.0977. Min Act: -0.1700
Data Index: 2585067 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 656318 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.0977. Min Act: -0.1700
Data Index: 6621879 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 775812 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.1290. Min Act: -0.1700
Data Index: 5377902 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1915. Min Range: -5.1915
Max Act: 5.0665. Min Act: -0.1700
Data Index: 1813286 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19