Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 351 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.8499. Min Act: -0.1700
Data Index: 4711511 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.6624. Min Act: -0.1700
Data Index: 1260610 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.5999. Min Act: -0.1700
Data Index: 2289235 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.5999. Min Act: -0.1700
Data Index: 3611106 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.5374. Min Act: -0.1700
Data Index: 5562931 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.5374. Min Act: -0.1700
Data Index: 2152903 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.4749. Min Act: -0.1700
Data Index: 40067 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.4749. Min Act: -0.1700
Data Index: 4230974 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.4749. Min Act: -0.1700
Data Index: 4116292 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.4124. Min Act: -0.1700
Data Index: 8005740 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.4124. Min Act: -0.1700
Data Index: 5617123 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 382838 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 3195535 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 3578441 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 4253851 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 1949316 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 6050325 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 4405786 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.4124. Min Act: -0.1700
Data Index: 3562624 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8499. Min Range: -8.8499
Max Act: 8.3499. Min Act: -0.1700
Data Index: 3102607 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19