Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.7107. Min Act: -0.1700
Data Index: 4039865 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.5857. Min Act: -0.1700
Data Index: 279745 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.4294. Min Act: -0.1700
Data Index: 7511341 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.3357. Min Act: -0.1700
Data Index: 1929082 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.3044. Min Act: -0.1700
Data Index: 3920805 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.3044. Min Act: -0.1700
Data Index: 7303008 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2107. Min Act: -0.1700
Data Index: 6975759 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2419. Min Act: -0.1700
Data Index: 7607605 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2419. Min Act: -0.1700
Data Index: 8531594 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2419. Min Act: -0.1700
Data Index: 3421411 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2419. Min Act: -0.1700
Data Index: 5238503 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2107. Min Act: -0.1700
Data Index: 5686569 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2107. Min Act: -0.1700
Data Index: 4169288 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2107. Min Act: -0.1700
Data Index: 8777703 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.2107. Min Act: -0.1700
Data Index: 6598954 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.1794. Min Act: -0.1700
Data Index: 8710475 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.1794. Min Act: -0.1700
Data Index: 6007156 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.1794. Min Act: -0.1700
Data Index: 5018558 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.1794. Min Act: -0.1700
Data Index: 4032481 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7107. Min Range: -6.7107
Max Act: 6.1794. Min Act: -0.1700
Data Index: 5602722 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19