Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.7988. Min Act: -0.1700
Data Index: 8186920 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.7362. Min Act: -0.1700
Data Index: 1951673 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.7362. Min Act: -0.1700
Data Index: 919513 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.7362. Min Act: -0.1700
Data Index: 7599752 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.7049. Min Act: -0.1700
Data Index: 875681 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.7049. Min Act: -0.1700
Data Index: 8419160 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.7049. Min Act: -0.1700
Data Index: 4207474 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.6736. Min Act: -0.1700
Data Index: 507733 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.6424. Min Act: -0.1700
Data Index: 7384280 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.6424. Min Act: -0.1700
Data Index: 3180582 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.6111. Min Act: -0.1700
Data Index: 688858 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.6111. Min Act: -0.1700
Data Index: 5769715 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.6111. Min Act: -0.1700
Data Index: 4306812 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.6111. Min Act: -0.1700
Data Index: 7003858 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.5798. Min Act: -0.1700
Data Index: 61515 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.5798. Min Act: -0.1700
Data Index: 2034514 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.5798. Min Act: -0.1700
Data Index: 5238754 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.5798. Min Act: -0.1700
Data Index: 5506544 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.5798. Min Act: -0.1700
Data Index: 2743634 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7988. Min Range: -3.7988
Max Act: 3.5328. Min Act: -0.1700
Data Index: 2193940 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19