Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5840 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.9384. Min Act: -0.1700
Data Index: 3449894 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8591. Min Act: -0.1700
Data Index: 3733479 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8591. Min Act: -0.1700
Data Index: 3075467 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8432. Min Act: -0.1700
Data Index: 4656710 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8432. Min Act: -0.1700
Data Index: 6894091 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8273. Min Act: -0.1700
Data Index: 7577016 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8273. Min Act: -0.1700
Data Index: 648221 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8273. Min Act: -0.1700
Data Index: 3065850 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8114. Min Act: -0.1700
Data Index: 5242782 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8114. Min Act: -0.1700
Data Index: 8467116 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8114. Min Act: -0.1700
Data Index: 5617996 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 188572 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8114. Min Act: -0.1700
Data Index: 3144978 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 8547325 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.8114. Min Act: -0.1700
Data Index: 7448155 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7796. Min Act: -0.1700
Data Index: 6498398 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 7470385 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 1382072 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 6451794 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9384. Min Range: -2.9384
Max Act: 2.7955. Min Act: -0.1700
Data Index: 6306813 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19