Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4034 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.9320. Min Act: -0.1700
Data Index: 5387066 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.9008. Min Act: -0.1700
Data Index: 8715257 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.8695. Min Act: -0.1700
Data Index: 4648378 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.8383. Min Act: -0.1700
Data Index: 5483804 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2017625 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.7133. Min Act: -0.1700
Data Index: 2378311 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.5883. Min Act: -0.1700
Data Index: 5059902 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.5570. Min Act: -0.1700
Data Index: 1745323 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.5258. Min Act: -0.1700
Data Index: 4204359 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.5258. Min Act: -0.1700
Data Index: 3203278 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4945. Min Act: -0.1700
Data Index: 3149324 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.5258. Min Act: -0.1700
Data Index: 7408588 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4945. Min Act: -0.1700
Data Index: 6057960 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4633. Min Act: -0.1700
Data Index: 283732 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4633. Min Act: -0.1700
Data Index: 3859077 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4633. Min Act: -0.1700
Data Index: 4770582 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4008. Min Act: -0.1700
Data Index: 2890924 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4320. Min Act: -0.1700
Data Index: 7116673 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.4008. Min Act: -0.1700
Data Index: 1370833 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9320. Min Range: -6.9320
Max Act: 6.3383. Min Act: -0.1700
Data Index: 3585370 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19