Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 84 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1249. Min Range: -6.1249
Max Act: 6.1249. Min Act: -0.1700
Data Index: 2034340 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.4999. Min Act: -0.1700
Data Index: 740740 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.4062. Min Act: -0.1700
Data Index: 4150781 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.3437. Min Act: -0.1700
Data Index: 6718560 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.3124. Min Act: -0.1700
Data Index: 6710396 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.3437. Min Act: -0.1700
Data Index: 8586002 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.2812. Min Act: -0.1700
Data Index: 6710395 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.2812. Min Act: -0.1700
Data Index: 6996941 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.2499. Min Act: -0.1700
Data Index: 6710397 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.1874. Min Act: -0.1700
Data Index: 718735 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.1562. Min Act: -0.1700
Data Index: 3684570 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.1249. Min Act: -0.1700
Data Index: 7471511 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0624. Min Act: -0.1700
Data Index: 2585649 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0624. Min Act: -0.1700
Data Index: 3143341 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0312. Min Act: -0.1700
Data Index: 5165845 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0312. Min Act: -0.1700
Data Index: 862438 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8074179 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0312. Min Act: -0.1700
Data Index: 7859498 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0312. Min Act: -0.1700
Data Index: 7526481 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1249. Min Range: -6.1249
Max Act: 5.0312. Min Act: -0.1700
Data Index: 5519920 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19