Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2409 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1663. Min Range: -8.1663
Max Act: 8.1663. Min Act: -0.1700
Data Index: 6850335 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1663. Min Range: -8.1663
Max Act: 8.1350. Min Act: -0.1700
Data Index: 6412670 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1663. Min Range: -8.1663
Max Act: 8.1038. Min Act: -0.1700
Data Index: 575372 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1663. Min Range: -8.1663
Max Act: 8.0413. Min Act: -0.1700
Data Index: 354426 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1663. Min Range: -8.1663
Max Act: 8.0100. Min Act: -0.1700
Data Index: 7839077 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.9163. Min Act: -0.1700
Data Index: 643339 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8850. Min Act: -0.1700
Data Index: 7950341 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8538. Min Act: -0.1700
Data Index: 4018902 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8538. Min Act: -0.1700
Data Index: 8620360 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8225. Min Act: -0.1700
Data Index: 4271181 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8850. Min Act: -0.1700
Data Index: 3151248 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8538. Min Act: -0.1700
Data Index: 1255820 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8538. Min Act: -0.1700
Data Index: 6002405 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8225. Min Act: -0.1700
Data Index: 1540124 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.7913. Min Act: -0.1700
Data Index: 7105464 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.7913. Min Act: -0.1700
Data Index: 4536804 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8225. Min Act: -0.1700
Data Index: 301908 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.7913. Min Act: -0.1700
Data Index: 954551 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.8225. Min Act: -0.1700
Data Index: 5589714 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1663. Min Range: -8.1663
Max Act: 7.7913. Min Act: -0.1700
Data Index: 424719 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19