Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1949 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.5562. Min Act: -0.1700
Data Index: 5770376 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.4625. Min Act: -0.1700
Data Index: 8139690 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.4625. Min Act: -0.1700
Data Index: 6694446 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.4312. Min Act: -0.1700
Data Index: 6571219 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.4000. Min Act: -0.1700
Data Index: 8395368 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.4000. Min Act: -0.1700
Data Index: 3684607 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.3375. Min Act: -0.1700
Data Index: 7770246 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.3375. Min Act: -0.1700
Data Index: 1836664 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.3062. Min Act: -0.1700
Data Index: 111465 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.3062. Min Act: -0.1700
Data Index: 4662871 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.3062. Min Act: -0.1700
Data Index: 6289278 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2750. Min Act: -0.1700
Data Index: 2525858 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2437. Min Act: -0.1700
Data Index: 7409057 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2750. Min Act: -0.1700
Data Index: 4040521 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2750. Min Act: -0.1700
Data Index: 2016892 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2750. Min Act: -0.1700
Data Index: 924087 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2750. Min Act: -0.1700
Data Index: 1298275 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2750. Min Act: -0.1700
Data Index: 4717201 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2125. Min Act: -0.1700
Data Index: 7222747 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5562. Min Range: -6.5562
Max Act: 6.2437. Min Act: -0.1700
Data Index: 6843874 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19