Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0029. Min Range: -5.0029
Max Act: 5.0029. Min Act: -0.1700
Data Index: 4116539 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.7841. Min Act: -0.1700
Data Index: 1620267 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5966. Min Act: -0.1700
Data Index: 5356147 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5654. Min Act: -0.1700
Data Index: 1562512 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5654. Min Act: -0.1700
Data Index: 7098065 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5654. Min Act: -0.1700
Data Index: 8134448 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5341. Min Act: -0.1700
Data Index: 6323047 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5654. Min Act: -0.1700
Data Index: 7321380 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5029. Min Act: -0.1700
Data Index: 3406253 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5029. Min Act: -0.1700
Data Index: 3202458 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.4716. Min Act: -0.1700
Data Index: 3342802 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5029. Min Act: -0.1700
Data Index: 1844823 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5029. Min Act: -0.1700
Data Index: 7703554 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.4716. Min Act: -0.1700
Data Index: 8342665 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.5029. Min Act: -0.1700
Data Index: 5091643 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.4716. Min Act: -0.1700
Data Index: 4943874 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.4716. Min Act: -0.1700
Data Index: 229700 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.4716. Min Act: -0.1700
Data Index: 6289316 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.4716. Min Act: -0.1700
Data Index: 3686181 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0029. Min Range: -5.0029
Max Act: 4.4716. Min Act: -0.1700
Data Index: 3571761 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19