Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 340 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4798. Min Act: -0.1700
Data Index: 5382870 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4173. Min Act: -0.1700
Data Index: 7814391 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 8817917 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 2431253 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 748331 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2298. Min Act: -0.1700
Data Index: 6664509 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 464835 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 5532208 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1636191 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1140374 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 6650114 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1673. Min Act: -0.1700
Data Index: 5264399 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1806935 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1673. Min Act: -0.1700
Data Index: 3611725 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 6664508 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 880819 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1361. Min Act: -0.1700
Data Index: 6424433 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 2141664 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 6995500 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1048. Min Act: -0.1700
Data Index: 988174 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19