Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 883 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0590. Min Range: -7.0590
Max Act: 7.0590. Min Act: -0.1700
Data Index: 7647866 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.9965. Min Act: -0.1700
Data Index: 2694566 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.9340. Min Act: -0.1700
Data Index: 7647869 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.7153. Min Act: -0.1700
Data Index: 2327642 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.7153. Min Act: -0.1700
Data Index: 312033 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.7153. Min Act: -0.1700
Data Index: 5254909 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6215. Min Act: -0.1700
Data Index: 3168599 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6528. Min Act: -0.1700
Data Index: 6217403 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6215. Min Act: -0.1700
Data Index: 7990755 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.6215. Min Act: -0.1700
Data Index: 2040169 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5590. Min Act: -0.1700
Data Index: 4203377 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5590. Min Act: -0.1700
Data Index: 1850730 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5590. Min Act: -0.1700
Data Index: 4736711 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5590. Min Act: -0.1700
Data Index: 361088 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5903. Min Act: -0.1700
Data Index: 431430 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5278. Min Act: -0.1700
Data Index: 3562105 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5278. Min Act: -0.1700
Data Index: 5368267 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.5278. Min Act: -0.1700
Data Index: 1816079 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4653. Min Act: -0.1700
Data Index: 5974912 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0590. Min Range: -7.0590
Max Act: 6.4340. Min Act: -0.1700
Data Index: 8811489 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19