Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1714. Min Range: -6.1714
Max Act: 6.1714. Min Act: -0.1700
Data Index: 4573544 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1714. Min Range: -6.1714
Max Act: 6.1714. Min Act: -0.1700
Data Index: 7419381 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1714. Min Range: -6.1714
Max Act: 6.1402. Min Act: -0.1700
Data Index: 6402111 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1714. Min Range: -6.1714
Max Act: 6.0777. Min Act: -0.1700
Data Index: 4884967 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1714. Min Range: -6.1714
Max Act: 6.0777. Min Act: -0.1700
Data Index: 5924893 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.9839. Min Act: -0.1700
Data Index: 2833913 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.9527. Min Act: -0.1700
Data Index: 8036529 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.9527. Min Act: -0.1700
Data Index: 91539 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.9214. Min Act: -0.1700
Data Index: 1972769 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.9527. Min Act: -0.1700
Data Index: 5317054 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.9214. Min Act: -0.1700
Data Index: 2957846 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.8902. Min Act: -0.1700
Data Index: 6000547 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.9214. Min Act: -0.1700
Data Index: 1408144 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.8589. Min Act: -0.1700
Data Index: 3189425 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.8277. Min Act: -0.1700
Data Index: 4285234 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.8277. Min Act: -0.1700
Data Index: 6433688 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.7964. Min Act: -0.1700
Data Index: 8008639 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.7964. Min Act: -0.1700
Data Index: 6970199 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.7964. Min Act: -0.1700
Data Index: 1339118 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1714. Min Range: -6.1714
Max Act: 5.7964. Min Act: -0.1700
Data Index: 4820776 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19