Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7998. Min Range: -7.7998
Max Act: 7.7998. Min Act: -0.1700
Data Index: 7699171 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7998. Min Range: -7.7998
Max Act: 7.2998. Min Act: -0.1700
Data Index: 8308871 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.9561. Min Act: -0.1700
Data Index: 8525579 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.9561. Min Act: -0.1700
Data Index: 4402984 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.8936. Min Act: -0.1700
Data Index: 2002589 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7998. Min Act: -0.1700
Data Index: 3833455 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7998. Min Act: -0.1700
Data Index: 8374060 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.8311. Min Act: -0.1700
Data Index: 2505366 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7686. Min Act: -0.1700
Data Index: 8372852 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7686. Min Act: -0.1700
Data Index: 2119612 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7686. Min Act: -0.1700
Data Index: 1116724 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7373. Min Act: -0.1700
Data Index: 6496332 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7373. Min Act: -0.1700
Data Index: 6882244 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.6748. Min Act: -0.1700
Data Index: 2091216 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7061. Min Act: -0.1700
Data Index: 4651201 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7061. Min Act: -0.1700
Data Index: 4093172 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.7061. Min Act: -0.1700
Data Index: 3753334 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.6748. Min Act: -0.1700
Data Index: 2045247 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.6748. Min Act: -0.1700
Data Index: 4569975 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7998. Min Range: -7.7998
Max Act: 6.6748. Min Act: -0.1700
Data Index: 379540 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19