Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.9594. Min Act: -0.1700
Data Index: 4744775 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.6469. Min Act: -0.1700
Data Index: 5698178 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.6157. Min Act: -0.1700
Data Index: 8342995 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.5844. Min Act: -0.1700
Data Index: 1251791 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.5844. Min Act: -0.1700
Data Index: 2056295 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.5532. Min Act: -0.1700
Data Index: 6477325 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.5532. Min Act: -0.1700
Data Index: 231000 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.5219. Min Act: -0.1700
Data Index: 4182836 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4907. Min Act: -0.1699
Data Index: 6061423 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4907. Min Act: -0.1700
Data Index: 36752 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4907. Min Act: -0.1700
Data Index: 6941281 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4907. Min Act: -0.1700
Data Index: 4878971 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4907. Min Act: -0.1700
Data Index: 456460 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4907. Min Act: -0.1700
Data Index: 3258866 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4594. Min Act: -0.1700
Data Index: 3293138 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.3969. Min Act: -0.1700
Data Index: 6879719 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4282. Min Act: -0.1700
Data Index: 2835347 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4282. Min Act: -0.1700
Data Index: 1659 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.4282. Min Act: -0.1700
Data Index: 3258862 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9594. Min Range: -6.9594
Max Act: 6.3969. Min Act: -0.1700
Data Index: 1394805 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19