Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1755. Min Act: -0.1700
Data Index: 7357717 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1130. Min Act: -0.1700
Data Index: 8605379 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.0193. Min Act: -0.1700
Data Index: 3948809 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1886623 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 4598101 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 8771960 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 7410803 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 6063856 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 404032 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8005. Min Act: -0.1700
Data Index: 427374 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8005. Min Act: -0.1700
Data Index: 7848165 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8005. Min Act: -0.1700
Data Index: 1209134 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 2889499 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 1229863 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 7714582 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 1824530 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 7338381 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 3850820 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 3681382 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 3073016 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19