Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1967 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.3603. Min Act: -0.1700
Data Index: 3657768 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.3603. Min Act: -0.1700
Data Index: 5071880 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.2978. Min Act: -0.1700
Data Index: 3217459 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.2353. Min Act: -0.1700
Data Index: 7505236 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.1728. Min Act: -0.1700
Data Index: 6061160 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.1103. Min Act: -0.1700
Data Index: 2854596 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.0791. Min Act: -0.1700
Data Index: 1059135 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.0791. Min Act: -0.1700
Data Index: 2642824 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.0791. Min Act: -0.1700
Data Index: 5418457 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.0478. Min Act: -0.1700
Data Index: 6914040 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.0478. Min Act: -0.1700
Data Index: 310967 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.0166. Min Act: -0.1700
Data Index: 7778288 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3603. Min Range: -6.3603
Max Act: 6.0166. Min Act: -0.1700
Data Index: 1818651 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3603. Min Range: -6.3603
Max Act: 5.9853. Min Act: -0.1700
Data Index: 5678099 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3603. Min Range: -6.3603
Max Act: 5.9541. Min Act: -0.1700
Data Index: 385212 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3603. Min Range: -6.3603
Max Act: 5.9541. Min Act: -0.1700
Data Index: 7439513 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3603. Min Range: -6.3603
Max Act: 5.9541. Min Act: -0.1700
Data Index: 7285503 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3603. Min Range: -6.3603
Max Act: 5.9541. Min Act: -0.1700
Data Index: 3827061 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3603. Min Range: -6.3603
Max Act: 5.9228. Min Act: -0.1700
Data Index: 1235802 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3603. Min Range: -6.3603
Max Act: 5.9228. Min Act: -0.1700
Data Index: 6175752 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19