Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5252 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.7490. Min Act: -0.1700
Data Index: 8567542 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.7021. Min Act: -0.1700
Data Index: 5684219 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.6552. Min Act: -0.1700
Data Index: 2499039 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.6708. Min Act: -0.1700
Data Index: 247889 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.6082. Min Act: -0.1700
Data Index: 5814540 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.6082. Min Act: -0.1700
Data Index: 2259553 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.5769. Min Act: -0.1700
Data Index: 6338981 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.5613. Min Act: -0.1700
Data Index: 3138370 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.5613. Min Act: -0.1700
Data Index: 1848515 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.5456. Min Act: -0.1700
Data Index: 8284335 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4986. Min Act: -0.1700
Data Index: 6103798 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4830. Min Act: -0.1700
Data Index: 2919829 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4673. Min Act: -0.1700
Data Index: 8729929 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4986. Min Act: -0.1700
Data Index: 5290614 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4830. Min Act: -0.1700
Data Index: 1396949 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4673. Min Act: -0.1700
Data Index: 4935176 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4360. Min Act: -0.1700
Data Index: 5631950 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4360. Min Act: -0.1700
Data Index: 4962992 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4360. Min Act: -0.1700
Data Index: 294620 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7490. Min Range: -3.7490
Max Act: 3.4360. Min Act: -0.1700
Data Index: 4666590 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19