Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1147 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 5415485 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1640. Min Act: -0.1700
Data Index: 1323609 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 5136538 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1327. Min Act: -0.1700
Data Index: 7163068 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0702. Min Act: -0.1700
Data Index: 1717228 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 6124684 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 7065082 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 1636061 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 1122005 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 5095936 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 1122010 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9452. Min Act: -0.1700
Data Index: 1122011 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 3874647 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9140. Min Act: -0.1700
Data Index: 4993844 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8827. Min Act: -0.1700
Data Index: 4538358 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8827. Min Act: -0.1700
Data Index: 1995826 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8827. Min Act: -0.1700
Data Index: 1122012 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8827. Min Act: -0.1700
Data Index: 1477101 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8827. Min Act: -0.1700
Data Index: 1122003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.8827. Min Act: -0.1700
Data Index: 2296456 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19