Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4421 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.7044. Min Act: -0.1700
Data Index: 2202497 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.6106. Min Act: -0.1700
Data Index: 5511383 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.6106. Min Act: -0.1700
Data Index: 1736035 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.5794. Min Act: -0.1700
Data Index: 4489684 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.5169. Min Act: -0.1700
Data Index: 7024019 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.4856. Min Act: -0.1700
Data Index: 3681687 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3606. Min Act: -0.1700
Data Index: 1283846 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 2446601 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 5718458 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.3294. Min Act: -0.1700
Data Index: 1213602 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2981. Min Act: -0.1700
Data Index: 6733363 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2981. Min Act: -0.1700
Data Index: 1977477 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2981. Min Act: -0.1700
Data Index: 6087569 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2669. Min Act: -0.1700
Data Index: 6706861 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2669. Min Act: -0.1700
Data Index: 3331073 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2356. Min Act: -0.1700
Data Index: 509414 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2356. Min Act: -0.1700
Data Index: 8269099 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2356. Min Act: -0.1700
Data Index: 3127300 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.2044. Min Act: -0.1700
Data Index: 3888078 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7044. Min Range: -6.7044
Max Act: 6.1419. Min Act: -0.1700
Data Index: 4519126 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19