Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.8481. Min Act: -0.1700
Data Index: 493389 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.8481. Min Act: -0.1700
Data Index: 8641027 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7856. Min Act: -0.1700
Data Index: 527484 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7856. Min Act: -0.1700
Data Index: 2873957 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7543. Min Act: -0.1700
Data Index: 1494110 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7543. Min Act: -0.1700
Data Index: 8392367 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7543. Min Act: -0.1698
Data Index: 8459900 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7543. Min Act: -0.1700
Data Index: 4999942 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7543. Min Act: -0.1699
Data Index: 5010243 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7543. Min Act: -0.1700
Data Index: 3000729 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7231. Min Act: -0.1700
Data Index: 5594658 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7543. Min Act: -0.1700
Data Index: 3607485 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7231. Min Act: -0.1700
Data Index: 356505 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.7231. Min Act: -0.1700
Data Index: 6125059 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6918. Min Act: -0.1700
Data Index: 5281860 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6918. Min Act: -0.1700
Data Index: 2057102 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6918. Min Act: -0.1700
Data Index: 5592092 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6918. Min Act: -0.1700
Data Index: 2768478 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6606. Min Act: -0.1700
Data Index: 598781 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8481. Min Range: -5.8481
Max Act: 5.6918. Min Act: -0.1700
Data Index: 2151501 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19