Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.8956. Min Act: -0.1700
Data Index: 8500267 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.8018. Min Act: -0.1700
Data Index: 5620282 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.6456. Min Act: -0.1700
Data Index: 3612329 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.5518. Min Act: -0.1700
Data Index: 6630154 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.5206. Min Act: -0.1700
Data Index: 1142549 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.4581. Min Act: -0.1700
Data Index: 191875 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.4581. Min Act: -0.1700
Data Index: 6837627 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3956. Min Act: -0.1700
Data Index: 6658221 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.4268. Min Act: -0.1700
Data Index: 1799217 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.4268. Min Act: -0.1700
Data Index: 4147996 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3643. Min Act: -0.1700
Data Index: 5228508 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3643. Min Act: -0.1700
Data Index: 3476105 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3331. Min Act: -0.1700
Data Index: 3388899 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3331. Min Act: -0.1700
Data Index: 8269535 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3331. Min Act: -0.1700
Data Index: 8069633 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3331. Min Act: -0.1700
Data Index: 6949355 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3331. Min Act: -0.1700
Data Index: 8676798 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3018. Min Act: -0.1700
Data Index: 2105387 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.3018. Min Act: -0.1700
Data Index: 1692545 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8956. Min Range: -6.8956
Max Act: 6.2706. Min Act: -0.1700
Data Index: 395829 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19