Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1000. Min Range: -6.1000
Max Act: 6.1000. Min Act: -0.1700
Data Index: 4472426 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.9437. Min Act: -0.1700
Data Index: 5934436 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.9437. Min Act: -0.1700
Data Index: 907093 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.9125. Min Act: -0.1700
Data Index: 476131 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.8812. Min Act: -0.1700
Data Index: 3704989 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.8812. Min Act: -0.1700
Data Index: 6664461 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.8500. Min Act: -0.1700
Data Index: 8115710 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.8500. Min Act: -0.1700
Data Index: 6861325 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.8187. Min Act: -0.1700
Data Index: 3621285 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.7875. Min Act: -0.1700
Data Index: 1040324 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.7562. Min Act: -0.1700
Data Index: 7447516 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.7562. Min Act: -0.1700
Data Index: 5453895 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.7250. Min Act: -0.1700
Data Index: 8385156 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.7250. Min Act: -0.1700
Data Index: 3595469 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.6937. Min Act: -0.1700
Data Index: 4176324 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.6625. Min Act: -0.1700
Data Index: 4420260 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.6625. Min Act: -0.1700
Data Index: 3721390 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.6312. Min Act: -0.1700
Data Index: 6355795 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6192382 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1000. Min Range: -6.1000
Max Act: 5.6625. Min Act: -0.1700
Data Index: 5997597 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19