Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.2525. Min Act: -0.1700
Data Index: 4024828 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 2122445 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 6180934 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0963. Min Act: -0.1700
Data Index: 2731619 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 2244967 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 3932410 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 5253979 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 1711993 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 6372663 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9400. Min Act: -0.1700
Data Index: 8352422 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9400. Min Act: -0.1700
Data Index: 4084070 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9088. Min Act: -0.1700
Data Index: 3042761 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9088. Min Act: -0.1700
Data Index: 2108833 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9088. Min Act: -0.1700
Data Index: 8181568 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9088. Min Act: -0.1700
Data Index: 3001632 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9088. Min Act: -0.1700
Data Index: 1128434 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.8775. Min Act: -0.1700
Data Index: 1980144 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.8775. Min Act: -0.1700
Data Index: 4524594 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.8775. Min Act: -0.1700
Data Index: 1457268 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.8775. Min Act: -0.1700
Data Index: 2650759 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19