Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4016 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.2248. Min Act: -0.1700
Data Index: 2051107 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.1311. Min Act: -0.1700
Data Index: 5630287 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0998. Min Act: -0.1700
Data Index: 8492901 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0998. Min Act: -0.1700
Data Index: 3501237 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0998. Min Act: -0.1700
Data Index: 6455834 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0998. Min Act: -0.1700
Data Index: 8484565 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0998. Min Act: -0.1700
Data Index: 2608262 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0686. Min Act: -0.1700
Data Index: 7949940 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0686. Min Act: -0.1700
Data Index: 5831150 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0686. Min Act: -0.1700
Data Index: 6070477 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0373. Min Act: -0.1700
Data Index: 3372817 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0373. Min Act: -0.1700
Data Index: 7234190 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0373. Min Act: -0.1700
Data Index: 8117000 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0061. Min Act: -0.1700
Data Index: 1796174 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0061. Min Act: -0.1700
Data Index: 8484564 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2248. Min Range: -5.2248
Max Act: 5.0061. Min Act: -0.1700
Data Index: 2482307 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2248. Min Range: -5.2248
Max Act: 4.9748. Min Act: -0.1700
Data Index: 5241982 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2248. Min Range: -5.2248
Max Act: 4.9748. Min Act: -0.1700
Data Index: 8421572 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2248. Min Range: -5.2248
Max Act: 4.9748. Min Act: -0.1700
Data Index: 5762508 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2248. Min Range: -5.2248
Max Act: 4.9748. Min Act: -0.1700
Data Index: 3383361 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19